SKILLEMALL.ai

BC skillguard

Security scanner for AgentSkill packages. Scan skills for credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques before installing them. Use when evaluating skills from ClawHub or any untrusted source.

modbender/skill-library-mcp Agent Skills author: modbender MIT 12 files body ≈ 292 tokens Open the sourcegithub.com analyzed 2 d ago

Security scanner for AgentSkill packages.

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
86
Quality 40%
83
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • medium Instruction override en-ignore-previous src/prompt-analyzer.js:99
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      { regex: /disregard\s+(?:all\s+)?(?:previous|prior|above|earlier)\s/gi, msg: 'Disregard previous instructions', severity: 'critical', weight: 30 },
      detector
    • low Risky intent intent-offensive-security README.md:26
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Privilege escalation (`sudo`, `chmod +s`, `/etc/shadow`)
    • low Risky intent intent-offensive-security README.md:118
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Reverse shell | `/dev/tcp`, `curl|bash`, cred harvesting | 0/100 🔴 | CAUGHT |
    • low Risky intent intent-offensive-security RED-TEAM-NOTES.md:1
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      # SkillGuard Red Team Notes
      detector
    • low Risky intent intent-offensive-security RED-TEAM-NOTES.md:111
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Phase 5: Red Team Gauntlet
    • low Dangerous commands cmd-privilege rules/dangerous-patterns.json:213
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      "setuid",
      code literal

    A further 4 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 12. 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 62/100

    • 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
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 8 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 292 tokens
    • 100Running it twice. No mutating operations

    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)
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • +1No license
    • +2Single-language instructions
    • +3Description length 243: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 8 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.