to-issues
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and process external data such as PRDs, plans, and feature descriptions (SKILL.md).
- Ingestion points: Processes user-provided or external project documentation as the primary input for generating task breakdowns.
- Boundary markers: The skill lacks instructions for the agent to use delimiters or to ignore potential instructions embedded within the processed documentation.
- Capability inventory: The issue template requires the agent to generate 'verification commands', which could be manipulated if the source material contains malicious command snippets.
- Sanitization: There are no instructions provided to validate or sanitize the content extracted from the source plans before it is formatted into issues or commands.
Audit Metadata