seo-geo

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted HTML content from external URLs, creating a vulnerability for indirect prompt injection where malicious instructions embedded in a website could attempt to hijack the agent's logic.\n
  • Ingestion points: Website content is ingested via scripts/seo_audit.py and curl commands in SKILL.md.\n
  • Boundary markers: The skill does not provide delimiters or system instructions to the agent to treat external content as data rather than instructions.\n
  • Capability inventory: The agent is granted Read, Write, and WebSearch tools, and can execute local Python scripts.\n
  • Sanitization: No sanitization is performed on the fetched content beyond basic regular expression extraction of meta tags.\n- [COMMAND_EXECUTION]: The skill relies on the execution of local processes, specifically a Python script (scripts/seo_audit.py) and common CLI utilities (curl, grep, open) to perform technical analysis and display results.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:12 PM