seo-audit
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core functionality of ingesting external website data.
- Ingestion points: As specified in SKILL.md, the skill fetches the target website's homepage and crawls up to 500 subsequent pages.
- Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions that might be embedded within the crawled HTML content.
- Capability inventory: The skill generates files (FULL-AUDIT-REPORT.md, ACTION-PLAN.md), captures screenshots, and executes a local script (scripts/fetch_page.py).
- Sanitization: No sanitization or validation logic is defined for the external content before it is processed by the orchestration or subagent logic.
Audit Metadata