seo-plan
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external PLAN.md files generated by multiple specialist skills (e.g., tech-seo-audit, aeo-audit, backlink-gap) stored in the plugin data directory. \n
- Ingestion points: Multiple file paths under ${CLAUDE_PLUGIN_DATA}/{brand}/seo/ where previous specialist outputs are stored. \n
- Boundary markers: The instructions do not specify the use of delimiters or safety instructions to treat the ingested PLAN.md content as untrusted. \n
- Capability inventory: The skill reads from and writes multiple markdown files to the filesystem and dispatches other specialist skills. \n
- Sanitization: There is no evidence of sanitization or validation of the content within the ingested specialist files. \n- [COMMAND_EXECUTION]: The skill references several local Python scripts for technical assessments. \n
- Evidence: Explicit mention of competitor-scraper.py, tech-seo-auditor.py, keyword_cluster.py, and content-scorer.py used for competitor site analysis and site health auditing.
Audit Metadata