public-release-verification
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to evaluate external data from repository baselines, deployment identifiers, and live public URLs, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via public URLs, SEO metadata, repository identities, and build artifacts as defined in SKILL.md and SKILL_CARD.md.
- Boundary markers: The skill body in SKILL.md does not specify the use of delimiters or 'ignore embedded instructions' warnings for the external data being verified.
- Capability inventory: The skill instructions imply the use of tools for repository inspection, network requests to verify HTTP routes, and browser-based verification (SKILL.md).
- Sanitization: No explicit sanitization, validation, or escaping requirements are defined for the content retrieved from external sources before it is analyzed by the agent.
Audit Metadata