yeet
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to instructions embedded in external data it processes, which could manipulate the agent into performing unauthorized code changes or merges.
- Ingestion points: The skill reads repository instructions, branch diffs, subagent review findings, and CI failure logs from the local environment (referenced in
SKILL.mdsteps 1, 2, and 4). - Boundary markers: The instructions do not specify the use of delimiters, XML tags, or system-level warnings to distinguish between the skill's instructions and the untrusted content being processed.
- Capability inventory: The agent has the authority to execute
git commit,git push, andgh pr merge, enabling it to persist and finalize code changes in the repository (SKILL.mdstep 5). - Sanitization: There are no explicit requirements in the skill to sanitize, escape, or validate data extracted from files or logs before using it in automated commit messages or shell command arguments.
Audit Metadata