bug-hunt
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing untrusted data from the user's project environment, which creates an attack surface for instructions embedded in source code or history.
- Ingestion points: The agent reads project code, callers, tests, commit history, logs, and existing issues/PRs as described in Sections 1 and 2 of SKILL.md.
- Boundary markers: No specific delimiters or instructions to disregard embedded commands in the analyzed data are defined.
- Capability inventory: The skill has the ability to execute project verification methods and gates (SKILL.md Sections 3 and 5), create git commits and branches, and perform network operations by opening pull requests and filing issues (SKILL.md Sections 5 and 6).
- Sanitization: The instructions do not specify any validation or sanitization of the content extracted from the project files before it is processed or included in automated outputs.
Audit Metadata