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
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:39 PM
Security Audit — agent-trust-hub — public-release-verification