SKILLEMALL.ai

BD clawskillguard

Security scanner for OpenClaw skills. Scans SKILL.md files and scripts for prompt injection, data exfiltration, malicious patterns, and unauthorized network calls. Use when a user asks to audit a skill, check skill security, scan for malicious code, verify skill safety, or before installing an untrusted skill.

ClawHub Agent Skills author: xeonai44 v1.0.2 MIT-0 3 files body ≈ 951 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
78
Quality 40%
82
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
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 · 18

    ✓ No critical or high findings

    Medium and low: 18
    • medium Instruction override en-ignore-previous SKILL.md:79
      Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
      - Instructions to ignore system prompts
      security skill
    • low Secrets in code secret-high-entropy-token scan.py:101
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ("XHUy…WZm",
      quoted
    • low Instruction override en-fake-system-prompt scan.py:106
      Fake system prompt injected into content (code comment; documentation of a security skill)
      # System prompt override
      commentsecurity skill
    • low Secrets in code secret-high-entropy-token scan.py:115
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      ("bmV3…XB0",
      detector
    • low Secrets in code secret-high-entropy-token scan.py:117
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      ("PFw8…XD5+",
      detector
    • low Secrets in code secret-high-entropy-token scan.py:153
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      ("KGNh…2gv",
      detector
    • low Secrets in code secret-high-entropy-token scan.py:164
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ("cm1c…ysv",
      quoted
    • low Risky intent intent-offensive-security SKILL.md:84
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Credential harvesting (reading .env, .ssh, tokens)
    • low Risky intent intent-offensive-security SKILL.md:90
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Privilege escalation attempts

    A further 9 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 3. 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 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 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
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 43 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 951 tokens

    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
    • -212 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +3Description length 311: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 43 items
    • +4Has examples (3 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: clean
    ClawSkillGuard is a local, user-directed skill scanner with auditability limitations but no evidence of hidden network access, data theft, persistence, or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026