article-links
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content, creating a surface for indirect instructions to influence the agent.
- Ingestion points: The agent is directed to audit rendered HTML, HTTP response headers, and article metadata (SKILL.md, references/rule.md).
- Boundary markers: There are no instructions provided to use delimiters or ignore embedded instructions when processing the external data.
- Capability inventory: The skill requires the agent to flag specific routes, describe verification steps, and use external SEO tools for validation (references/rule.md).
- Sanitization: The instructions lack any requirement for sanitizing, escaping, or validating the ingested HTML or metadata before the agent processes it.
Audit Metadata