seo-optimize
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text or content from URLs, creating a surface for potential indirect prompt injection attacks. An attacker could embed malicious instructions in a draft that the agent is asked to optimize.
- Ingestion points: User-supplied content (pasted text or URL) processed during the optimization method.
- Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate user-provided data from the agent's instructions.
- Capability inventory: The skill has file-read capabilities (reading .agents/blog-context.md and house-style/references/ai-tells.md) and likely network-read capabilities to fetch content from URLs.
- Sanitization: There is no mention of sanitizing or validating the input content to prevent instructions from being misinterpreted by the agent.
Audit Metadata