resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and understand external, potentially untrusted data such as pull request descriptions, commit messages, and issues to determine the intent of conflicting changes.
- Ingestion points: SKILL.md (Step 2) directs the agent to check PRs and issues.
- Boundary markers: None provided to distinguish between instructions and data.
- Capability inventory: SKILL.md (Step 4 & 5) includes running automated checks (tests/formatters) and committing files.
- Sanitization: No sanitization of ingested content is mentioned.
- [COMMAND_EXECUTION]: The skill encourages the execution of project-specific automated checks, such as tests and typecheckers.
- Evidence: Step 4 in SKILL.md ("Discover the project's automated checks and run them..."). While this is an intended function for code maintenance, it involves running code present in the workspace which could be compromised in a shared repository context.
Audit Metadata