SKILLEMALL.ai
GitHub ↗ RU Sign in

CD ClawTrial Courtroom

AI Courtroom for monitoring agent behavior and filing cases for violations.

modbender/skill-library-mcp Agent Skills author: modbender MIT 44 files body ≈ 811 tokens Open the sourcegithub.com↗ analyzed 2 d ago

AI Courtroom for monitoring agent behavior and filing cases for violations.

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureAI and agentstype 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
C
71/100
safety, quality, tests
Safety 60%
78
Quality 40%
61
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 10

✓ No critical or high findings

Medium and low: 10
  • medium Instruction override en-ignore-previous scripts/setup-cron.js:26
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    - **Jailbreak Attempts**: User trying to bypass safety guidelines
    quoted
  • medium Instruction override en-ignore-previous scripts/trigger-evaluation.js:43
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    4. **Jailbreak Attempts**: User trying to bypass safety guidelines
    quoted
  • medium Instruction override en-ignore-previous src/evaluator.js:199
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    - **Jailbreak Attempts**: User trying to bypass safety guidelines
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:289
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…ywo+qwL+oL8H…C1U+vRfLQDvw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:305
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-Yqfm+XDx0+Prh3…1yC+JWZ2…IL7+vK+Clp7…D7g==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:318
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…xZl+RoGR…fbT/ZgrF…0EA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:331
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…3bJ+V0If…IXN+CL65…a4w==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:347
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…H47+FFon…OsV/4+RRsz…0ig==",
    quoted
  • low Dangerous commands cmd-cron-mention scripts/clawtrial.js:619
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    const currentCrontab = execSync('crontab -l 2>/dev/null || echo ""', { encoding: 'utf8' });
    quoted
  • low Dangerous commands cmd-cron-mention scripts/setup-cron.js:108
    Mentions editing / listing crontab (string literal in code, not executed)
    console.log('Add this to your crontab (crontab -e):\n');
    code literal

Files scanned: 44. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (ClawTrial Courtroom) differs from the folder (clawtrial)
  • 100Tools and files. No external tools needed
  • 100Steps. 19 steps
  • 100Execution cost. Instruction body is 811 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill

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 75: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -37 of 7 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.