FD biomcp-server

(no description)

FreedomIntelligence/OpenClaw-Medical-Skills Agent Skills author: FreedomIntelligence 80 files · 4 scripts body ≈ 585 tokens Open the sourcegithub.com↗ analyzed 11 h ago

<!--

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

Integration Infrastructure AI and agents Software developmenttype and topics are labelled automatically from the skill text

Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode

JSON

Technical rating

0/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 0
Run on models: none yet

Process rating

39/100

Unfinished process

Result and completion w 14: 0
When it triggers w 12: 0
Inputs and preconditions w 11: 0

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Add a description to the frontmatter: without it the skill never triggers.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 75

✓ No critical or high findings

Medium and low: 75

medium Exfiltration net-credential-use repo/docs/developer-guides/01-server-deployment.md:540

Credential used in a network call (verify the destination is the intended service)
```
curl -H "X-API-KEY: $NCI_API_KEY" https://api.cancer.gov/v2/trials
```
medium Dangerous commands cmd-pipe-to-shell-known-host repo/docs/getting-started/01-quickstart-cli.md:29

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -LsSf https://astral.sh/uv/install.sh | sh
```
medium Dangerous commands cmd-pipe-to-shell-known-host repo/docs/getting-started/02-desktop-integration.md:35

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -LsSf https://astral.sh/uv/install.sh | sh
```
medium Dangerous commands cmd-pipe-to-shell-known-host repo/docs/troubleshooting.md:29

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -LsSf https://astral.sh/uv/install.sh | sh
```
medium Dangerous commands cmd-pipe-to-shell-known-host repo/docs/troubleshooting.md:39

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -LsSf https://astral.sh/uv/install.sh | sh
```
medium Dangerous commands cmd-shell-rc repo/docs/troubleshooting.md:124

Writes to a shell startup file
```
echo 'export NCI_API_KEY="your-key-here"' >> ~/.bashrc
```
medium Exfiltration net-credential-use repo/docs/troubleshooting.md:141

Credential used in a network call (verify the destination is the intended service)
```
curl -H "X-API-KEY: $NCI_API_KEY" \
```
low Secrets in code secret-high-entropy-token bio_mcp_server.py:76

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
__AUTHOR_SIGNATURE__ = "9a7f…URE"
```
detector
low Secrets in code secret-high-entropy-token README.md:49

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/BIOMCP_DATA_FLOW.md:279

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/CHANGELOG.md:463

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/apis/error-codes.md:411

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/apis/overview.md:128

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/apis/python-sdk.md:513

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/01-overview.md:215

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/02-biothings-suite.md:497

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/03-cbioportal.md:157

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/04-clinicaltrials-gov.md:150

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/05-nci-cts-api.md:469

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/06-pubtator3.md:226

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/backend-services-reference/07-alphagenome.md:482

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/blog/ai-assisted-clinical-trial-search-analysis.md:93

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/blog/researcher-persona-resource.md:169

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/changelog.md:406

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/concepts/01-what-is-biomcp.md:66

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/concepts/02-the-deep-researcher-persona.md:234

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/concepts/03-sequential-thinking-with-the-think-tool.md:255

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Dangerous commands cmd-background-process repo/docs/developer-guides/01-server-deployment.md:114

Starts a background / autostarted process
```
sudo systemctl enable biomcp
```
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/01-server-deployment.md:567

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/02-contributing-and-testing.md:730

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
```

```
detectorfixture
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/03-third-party-endpoints.md:363

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/04-transport-protocol.md:302

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/05-error-handling.md:205

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/06-http-client-and-caching.md:260

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/07-performance-optimizations.md:154

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/developer-guides/generate_endpoints.py:46

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
__AUTHOR_SIGNATURE__ = "9a7f…URE"
```
detector
low Secrets in code secret-high-entropy-token repo/docs/faq-condensed.md:102

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/FDA_SECURITY.md:305

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/genomoncology.md:63

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/getting-started/01-quickstart-cli.md:243

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/getting-started/02-desktop-integration.md:308

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/getting-started/03-authentication-and-api-keys.md:361

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/01-find-articles-and-cbioportal-data.md:338

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/02-find-trials-with-nci-and-biothings.md:447

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/03-get-comprehensive-variant-annotations.md:506

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/04-predict-variant-effects-with-alphagenome.md:602

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/05-logging-and-monitoring-with-bigquery.md:203

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/how-to-guides/06-search-nci-organizations-and-interventions.md:700

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/index.md:266

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Risky intent intent-offensive-security repo/docs/policies.md:186

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
- Authentication bypass or privilege escalation
```
low Secrets in code secret-high-entropy-token repo/docs/policies.md:412

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/reference/architecture-diagrams.md:233

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/reference/quick-architecture.md:74

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/reference/quick-reference.md:432

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/reference/visual-architecture.md:100

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/troubleshooting.md:503

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/tutorials/alphagenome-variant-analysis.md:262

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/tutorials/biothings-prompts.md:378

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/tutorials/nci-prompts.md:328

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector
low Secrets in code secret-high-entropy-token repo/docs/tutorials/openfda-integration.md:413

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```

```
detector

…and 15 more

Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

error frontmatter SKILL.md: no YAML frontmatter block found
error name-missing SKILL.md: frontmatter has no `name`
error description-missing SKILL.md: no `description` — the skill can never trigger

Process rating: all ten parameters 39/100

0Result and completion. Does not say what the result is
0When it triggers. No condition that starts the skill
0Inputs and preconditions. Does not say what the process needs to start
0Failures and branches. Linear process with no failure handling
0Progress reporting. Says nothing while it works
30Running it twice. 3 mutating operations with no state check
60Tools and files. Uses tools (web, python) that frontmatter does not declare
85Steps. 23 steps, 2 vague phrases
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 585 tokens

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Description length 0: 120–800 characters recommended
+3Output format is not stated: the model decides each time
+4No input/output examples
+1No license
+2Single-language instructions
+4Structure: 13 headings
+3Step-by-step instructions: 23 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 80

README.md 1K
SKILL.md 2K
bio_mcp_server.py 3K
repo/.github/actions/setup-python-env/action.yml 1K
repo/.github/dependabot.yml 0K
repo/.github/workflows/ci.yml 4K
repo/.github/workflows/deploy-docs.yml 1K
repo/.github/workflows/on-release-main.yml 2K
repo/.github/workflows/validate-codecov-config.yml 0K
repo/.gitignore 2K
repo/.pre-commit-config.yaml 1K
repo/BIOMCP_DATA_FLOW.md 8K
repo/CHANGELOG.md 15K
repo/Dockerfile 1K
repo/LICENSE 1K
repo/Makefile 3K
repo/codecov.yaml 0K
repo/docker-compose.yml 0K
repo/docs/FDA_SECURITY.md 9K
repo/docs/apis/error-codes.md 13K
repo/docs/apis/overview.md 4K
repo/docs/apis/python-sdk.md 13K
repo/docs/assets/mcp_architecture.txt 2K
repo/docs/backend-services-reference/01-overview.md 6K
repo/docs/backend-services-reference/02-biothings-suite.md 11K
repo/docs/backend-services-reference/03-cbioportal.md 5K
repo/docs/backend-services-reference/04-clinicaltrials-gov.md 7K
repo/docs/backend-services-reference/05-nci-cts-api.md 10K
repo/docs/backend-services-reference/06-pubtator3.md 7K
repo/docs/backend-services-reference/07-alphagenome.md 12K
repo/docs/blog/ai-assisted-clinical-trial-search-analysis.md 4K
repo/docs/blog/researcher-persona-resource.md 7K
repo/docs/changelog.md 13K
repo/docs/concepts/01-what-is-biomcp.md 3K
repo/docs/concepts/02-the-deep-researcher-persona.md 7K
repo/docs/concepts/03-sequential-thinking-with-the-think-tool.md 8K
repo/docs/developer-guides/01-server-deployment.md 10K
repo/docs/developer-guides/02-contributing-and-testing.md 15K
repo/docs/developer-guides/03-third-party-endpoints.md 13K
repo/docs/developer-guides/04-transport-protocol.md 7K
repo/docs/developer-guides/05-error-handling.md 5K
repo/docs/developer-guides/06-http-client-and-caching.md 6K
repo/docs/developer-guides/07-performance-optimizations.md 4K
repo/docs/developer-guides/generate_endpoints.py 1K
repo/docs/faq-condensed.md 3K
repo/docs/genomoncology.md 3K
repo/docs/getting-started/01-quickstart-cli.md 6K
repo/docs/getting-started/02-desktop-integration.md 8K
repo/docs/getting-started/03-authentication-and-api-keys.md 9K
repo/docs/how-to-guides/01-find-articles-and-cbioportal-data.md 8K
repo/docs/how-to-guides/02-find-trials-with-nci-and-biothings.md 11K
repo/docs/how-to-guides/03-get-comprehensive-variant-annotations.md 12K
repo/docs/how-to-guides/04-predict-variant-effects-with-alphagenome.md 16K
repo/docs/how-to-guides/05-logging-and-monitoring-with-bigquery.md 7K
repo/docs/how-to-guides/06-search-nci-organizations-and-interventions.md 18K
repo/docs/index.md 8K
repo/docs/policies.md 14K
repo/docs/reference/architecture-diagrams.md 11K
repo/docs/reference/quick-architecture.md 4K
repo/docs/reference/quick-reference.md 9K

When to use

- Unified literature search (PubMed/PMC) inside MCP clients. - Entity normalization via PubTator3 or genomic variant lookups. - ClinicalTrials.gov queries without bespoke API wrappers.

Dates

In catalog since —

Updated in catalog 21 Jul 2026

First seen here 4 Oct 2026

Last analysis 4 Oct 2026, 22:03 UTC

Last seen in crawl 11 h ago

Score history

Date		Score	Safety	Qual.
4 Oct 2026	F	0	0	0

For the author: a README badge

html

The badge shows today's grade: if the skill changes, so does it. More.