pavlo-release-announcer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external commits, tickets, and plans to generate release announcements.
- Ingestion points: Commit messages, ticket descriptions, and project plans referenced in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or safety markers to isolate the agent from instructions potentially embedded in the source data.
- Capability inventory: The skill is restricted to using the show_content tool (SKILL.md) to present information. It does not have access to file-writing, network communication, or shell execution tools.
- Sanitization: There is no evidence of sanitization or escaping applied to the external content before it is processed by the agent.
Audit Metadata