seo-team-the-general
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including competitor website content and search engine results, which could contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: The skill fetches competitor page depth and structure in Step 4 and AI-generated responses from various LLMs in Step 6.
- Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when processing or summarizing external website content.
- Capability inventory: The skill has the capability to write files to the local workspace directory and execute commands via the
seoclitool. - Sanitization: There is no evidence of content sanitization or filtering applied to external data before it is presented to the agent for analysis.
Audit Metadata