directory-submissions
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to research and evaluate external directories, marketplaces, and registries. This task requires processing untrusted third-party content, which could contain adversarial instructions intended to subvert the agent's behavior.
- Ingestion points: External directory websites, submission guidelines, and platform community pages are processed during the selection and preparation phases described in references/directory-workflow.md.
- Boundary markers: No specific boundary markers or 'ignore' instructions are provided to help the agent distinguish between its system instructions and data retrieved from the web.
- Capability inventory: The skill does not provide custom scripts, but the workflow implies the use of a browser or search tool to collect destination site data.
- Sanitization: The instructions do not specify any validation or sanitization protocols for the information gathered from external sources.
Audit Metadata