antislop
Warn
Audited by Snyk on Jun 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's refresh workflow explicitly runs at runtime and curl-fetches live wikitext from Wikipedia (e.g. https://en.wikipedia.org/w/api.php?action=parse&page=Wikipedia:Signs_of_AI_writing&prop=wikitext&format=json and https://en.wikipedia.org/w/api.php?action=parse&page=Wikipedia:WikiProject_AI_Cleanup&prop=wikitext&format=json), parses that content, and uses it to update detection rules that directly control the agent's prompt/behavior.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata