SKILLEMALL.ai
GitHub ↗ RU Sign in

BC canary

Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on startup, deep scans on demand. Fixes issues with your permission.

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files body ≈ 10 917 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on…

As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

IntegrationAWSStripeSlackGitHubSecuritytype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
84
Quality 40%
62
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
30
Execution cost w 6
40
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.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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

✓ No critical or high findings

Medium and low: 4
  • medium Exfiltration exfil-webhook-url SKILL.md:214
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | Slack Webhook | `https://hooks.slack.com/` | URL |
    table
  • medium Exfiltration exfil-webhook-url SKILL.md:215
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | Discord Webhook | `https://discord.com/api/webhooks/` | URL |
    table
  • medium Exfiltration exfil-webhook-url SKILL.md:236
    Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation table row)
    | Generic Webhook | `https://webhook.site/` | URL |
    table
  • low Secrets in code secret-aws-key SKILL.md:202
    AWS access key ID (placeholder value)
    | AWS Access Key | `AKIA` | `AKIA…PLE` |
    placeholder

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 10917 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 62/100

  • 0Result and completion. Does not say what the result is
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 10917 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 164 steps, 2 vague phrases
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (15 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 219: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 164 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.