SKILLEMALL.ai
GitHub ↗ RU Sign in

BC secure-skill

Scan skills in a project directory for security issues and generate a markdown table report, then install skills from a local registry. Combines static analysis of code and markdown files with supply chain checks. Use when auditing a skills directory, generating a security summary table, or installing skills from a local registry.

ClawHub Agent Skills author: Garsonjw v1.0.0 MIT-0 5 files body ≈ 714 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Scan skills in a project directory for security issues and generate a markdown table report, then install skills from a local registry.

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

GeneratorData and analyticstype 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
83/100
safety, quality, tests
Safety 60%
80
Quality 40%
88
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
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

    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 Instruction override en-ignore-previous scripts/patterns.json:66
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      {"regex": "ignore\\s+(all\\s+)?previous\\s+instructions", "risk": "Attempts to override system prompt", "fix": "Remove this phrase"},
      detector
    • medium Instruction override en-ignore-previous scripts/patterns.json:67
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      {"regex": "ignore\\s+(all\\s+)?prior\\s+instructions", "risk": "Attempts to override system prompt", "fix": "Remove this phrase"},
      detector
    • medium Instruction override en-ignore-previous scripts/patterns.json:68
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      {"regex": "disregard\\s+(all\\s+)?(previous|prior|above)", "risk": "Disregard existing instructions", "fix": "Remove this directive"},
      detector
    • medium Instruction override en-fake-system-prompt scripts/patterns.json:69
      Fake system prompt injected into content (detector / deny-list definition)
      {"regex": "new\\s+system\\s+prompt", "risk": "Injects a replacement system prompt", "fix": "Remove system prompt override"},
      detector

    Files scanned: 5. 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 61/100

    • 0Result and completion. Does not say what the result is
    • 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
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 8 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 714 tokens
    • 100Running it twice. Mutating operations check current state

    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
    • +2Single-language instructions
    • +3Description length 332: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 8 items
    • +4Has examples (7 code blocks)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    This skill is a scanner that also installs and can replace local skills automatically, despite parts of its documentation describing scanning as read-only.
    LLM: suspicious (high) · VirusTotal: · 14 Jul 2026