to-issues
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from external sources and can perform write actions based on that data.\n
- Ingestion points: The skill fetches and reads data from an issue tracker (including issue bodies and comments) and reads files from the codebase (SKILL.md, Step 1 and Step 2).\n
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the data fetched from the issue tracker or codebase.\n
- Capability inventory: The agent has the ability to read files from the filesystem and create new issues on the project's issue tracker.\n
- Sanitization: There is no evidence of sanitization, filtering, or validation performed on the external content before it is used to generate new issues.\n- [COMMAND_EXECUTION]: The instructions direct the agent to inform the user to run a specific setup command,
/setup-matt-pocock-skills, which constitutes an external dependency for environment configuration.
Audit Metadata