create-pull-request
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git logs and diffs which could potentially contain malicious instructions from external contributors. The ingestion points are artifacts produced by the collection script. The risk is mitigated by Phase 4's Chain-of-Verification and Phase 6's mandatory user approval requirement. No explicit boundary markers are used to isolate the git data. Capabilities include local shell execution for git and platform CLI tools.
- [COMMAND_EXECUTION]: The skill executes local repository scripts and standard tools such as git, gh, glab, and rg. These operations are conducted within the local environment and impactful actions are gated by explicit user consent.
Audit Metadata