seo-reposition
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill initiates local shell scripts including
serp_check.pyfor search data retrieval andindependent_review.shfor strategic audits.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of external data from search engine results, which introduces a surface for indirect prompt injection.\n - Ingestion points: External content is fetched from search engine result pages (SERPs) and Google Search Console (GSC) through tools like
serp_check.py.\n - Boundary markers: No explicit delimiters or instructions are specified to help the model ignore potentially malicious instructions embedded within the search data.\n
- Capability inventory: The skill is capable of executing shell scripts and performing file system operations, such as writing findings and wording guides.\n
- Sanitization: The instructions do not define any sanitization or validation steps for the content retrieved from external search engines before it is processed by the agent.
Audit Metadata