seo-google
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, such as webpage content for NLP analysis and YouTube video comments. This creates a surface for indirect prompt injection where malicious instructions in external content could attempt to influence the agent.\n
- Ingestion points:
nlp_analyze.py(URL and text analysis) andyoutube_search.py(fetching video comments).\n - Boundary markers: No explicit delimiters or instructions are mentioned for segregating external data in the provided documentation.\n
- Capability inventory: The skill queries multiple Google APIs and generates reports based on the collected data.\n
- Sanitization: Content sanitization or validation of external content is not detailed in the provided references.\n- [COMMAND_EXECUTION]: The skill uses the
claude-seocommand-line utility to run several Python scripts designed for API interactions. These scripts are core components of the skill's functionality and are treated as vendor-owned resources.
Audit Metadata