SKILLEMALL.ai
GitHub ↗ RU Sign in

DD paperclip

Searches and reads biomedical papers, FDA/PMDA/EMA documents, clinical trials, and protein records with the GXL Paperclip CLI and Python SDK. Supports source-scoped search, full-text grep, metadata SQL, map/reduce extraction, figure analysis, optional repositories and claim verification, and line-pinned citations. Use when a task names GXL paperclip, asks to install or authenticate it, or requests literature retrieval and evidence extraction through Paperclip.

Not recommendedcritical or high security findings · low grade D
K-Dense-AI/claude-scientific-skills Agent Skills author: K-Dense-AI MIT 7 files body ≈ 2 919 tokens Open the sourcegithub.com↗ analyzed 12 h ago

Searches and reads biomedical papers, FDA/PMDA/EMA documents, clinical trials, and protein records with the GXL Paperclip CLI and Python SDK.

As a process D 48/100 · Unfinished process — weak spots: steps, result and completion, when it triggers

IntegrationResearchSoftware developmentAI and agentstype 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
D
67/100
safety, quality, tests
Safety 60%
54
Quality 40%
86
Run on models
none yet
Process rating
D
48/100
Unfinished process
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 4

  • high Exfiltration exfil-send-secrets-to-url references/installation.md:155
    Instruction to send secrets/history to an external endpoint ("only send to …" — scoping, not exfiltration)
    Only send credentials to the server selected for the task.
    scoped
  • high Dangerous commands cmd-install-from-url references/python-sdk.md:15
    Installs a package from an untrusted URL / archive
    uv pip install https://paperclip.gxl.ai/paperclip.whl
Medium and low: 2
  • medium Dangerous commands cmd-pipe-to-shell references/installation.md:13
    Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
    curl -fsSL https://paperclip.gxl.ai/install.sh | bash
    vendor-host
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 48/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 9 mutating operations with no state check
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2919 tokens
  • 100Progress reporting. Reports progress

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)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 464: enough signal without eating the budget
  • +4Structure: 12 headings
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.