hunt-regressions
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script located at
../../scripts/registry.pywith thecandidateargument to manage regression IDs as part of its core workflow. - [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and process external, untrusted data (PR discussions and change messages) which could contain hidden malicious instructions.
- Ingestion points: Reads PR discussions and change messages (SKILL.md).
- Boundary markers: Absent; no delimiters or ignore-instructions are specified for the external data.
- Capability inventory: The skill can execute local scripts (
registry.py) and write files to the filesystem (hunt.json, candidate files). - Sanitization: Absent; there are no instructions to sanitize or validate the content of the PR discussions before processing.
Audit Metadata