Caveat verdict

wiki2doc

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill hardcodes a Confluence username and plaintext password in the published documentation, constituting a credential exposure risk even for an internal intranet tool.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

33
security
50
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match critical

Possible hardcoded credential

README.md · code · PASSWORD = "Aa123123

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://10.225.1.76

Pattern match medium

subprocess execution — runs system commands from Python

bin/wiki2testcases.py · prose · downgraded · subprocess.run(

Pattern match low

Python shutil file operation — copies/moves/deletes files

bin/wiki2doc.py · prose · downgraded · shutil.rmtree(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

agent_memorypackage_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API