30x-seo-internal-links
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites to perform SEO link analysis, which creates a potential surface for malicious instructions embedded in the crawled content to influence the agent.
- Ingestion points: External website content crawled using the
WebFetchtool (SKILL.md). - Boundary markers: The skill lacks explicit delimiters or instructions to ignore commands within the fetched data.
- Capability inventory: The skill is authorized to use
WebFetchandReadtools to process site content. - Sanitization: No input sanitization, escaping, or instruction-filtering is specified for the ingested website data.
Audit Metadata