SKILLEMALL.ai
GitHub ↗ RU Sign in

FF Canary Agent Safety Tripwire System

Safety monitoring and tripwire detection for AI agents. Protects against unauthorized file access, dangerous commands, and excessive activity. Auto-halts on critical violations. Honeypot tripwires detect snooping.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Shadow Rose v1.0.8 MIT-0 10 files body ≈ 3 575 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 33/100 · Will not run — References files that are not bundled: LICENSE

AnalyzerGitHubAWSSecuritytype 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
F
24/100
safety, quality, tests
Safety 60%
0
Quality 40%
61
Run on models
none yet
Process rating
F
33/100
Will not run
References files that are not bundled: LICENSE
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The text references files that are not there: add them or drop the references.
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 · 13

  • critical Dangerous commands cmd-destructive-fs LIMITATIONS.md:146
    Destructive filesystem command (wipes root/home/drive)
    rm -rf /
  • critical Dangerous commands cmd-encoded-exec LIMITATIONS.md:149
    Executes a base64/encoded payload
    echo "cm0gLXJmIC8=" | base64 -d | sh  # Decodes to "rm -rf /"
  • high Dangerous commands cmd-encoded-exec LIMITATIONS.md:155
    Executes a base64/encoded payload (detector / deny-list definition)
    - Add patterns for common encoding patterns (`base64 -d`, `echo | sh`)
    detector
Medium and low: 10
  • low Exfiltration exfil-webhook-url config_example.py:139
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    # alert_webhook = 'https://hooks.slack.com/...'
    placeholder
  • low Exfiltration exfil-webhook-url LIMITATIONS.md:50
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    requests.post('https://hooks.slack.com/...', json={
    placeholder
  • low Dangerous commands cmd-pipe-to-shell README.md:26
    Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)
    - Detects `rm -rf /`, `chmod 777`, `curl | sh`, etc.
    negated
  • low Dangerous commands cmd-privilege README.md:26
    Privilege escalation / world-writable permissions (negated — the text forbids it)
    - Detects `rm -rf /`, `chmod 777`, `curl | sh`, etc.
    negated
  • low Dangerous commands cmd-privilege README.md:397
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    assert not canary.check_command('chmod 777 /tmp')[0]
    quoted
  • low Risky intent intent-offensive-security README.md:463
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    is NOT a replacement for professional security auditing, penetration testing, or
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:40
    Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)
    - Detects `rm -rf /`, `chmod 777`, `curl | sh`, etc.
    negated
  • low Dangerous commands cmd-privilege SKILL.md:40
    Privilege escalation / world-writable permissions (negated — the text forbids it)
    - Detects `rm -rf /`, `chmod 777`, `curl | sh`, etc.
    negated
  • low Dangerous commands cmd-privilege SKILL.md:412
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    assert not canary.check_command('chmod 777 /tmp')[0]
    quoted
  • low Risky intent intent-offensive-security SKILL.md:496
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    is NOT a replacement for professional security auditing, penetration testing, or

Files scanned: 10. 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")
  • warning missing-ref reference to a missing file: LICENSE
  • note frontmatter-key unknown frontmatter key "slug"

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: LICENSE
  • 0Tools and files. 1 referenced file(s) missing: LICENSE
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 13 mutating operations with no state check
  • 40Consistency. Frontmatter name (Canary Agent Safety Tripwire System) differs from the folder (canary-sr)
  • 55Failures and branches. 1 branches
  • 85Steps. 61 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 3575 tokens
  • 100Progress reporting. Reports progress
  • low 16 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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 213: enough signal without eating the budget
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 61 items
  • +4Has examples (14 code blocks)
  • +1License stated

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

External checks

ClawHub: clean
Canary is a disclosed local safety-monitoring helper, but users should treat it as advisory logging and checks, not a real sandbox or kill switch.
LLM: benign (high) · VirusTotal: · 29 May 2026