antislop

Fail

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The SKILL.md file contains a "Pattern Refresh Protocol" section that instructs the agent to fetch wikitext data from Wikipedia using curl and pipe the output directly into a python3 command for processing. This pattern of remote data ingestion coupled with local script execution is a high-risk behavior often associated with supply chain attacks.
  • [COMMAND_EXECUTION]: The skill provides explicit shell commands for the agent to run, including the use of curl, python3, and a gemini CLI tool. These instructions are intended to update the skill's internal logic based on external data.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates fetching data from external Wikipedia API endpoints (en.wikipedia.org/w/api.php) to dynamically refresh its list of AI writing patterns.
Recommendations
  • HIGH: Downloads and executes remote code from: https://en.wikipedia.org/w/api.php?action=parse&page=Wikipedia:WikiProject_AI_Cleanup&prop=wikitext&format=json, https://en.wikipedia.org/w/api.php?action=parse&page=Wikipedia:Signs_of_AI_writing&prop=wikitext&format=json - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 13, 2026, 07:00 AM