resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions (Step 2 in SKILL.md) direct the agent to analyze commit messages, PRs, and original issues/tickets to understand the intent of conflicting changes. This external data constitutes an attack surface for indirect prompt injection, where an attacker could embed malicious instructions in a PR or issue that the agent might follow while resolving conflicts.
- Ingestion points: Git history, commit messages, pull request content, and issue trackers are read and processed by the agent.
- Boundary markers: No specific delimiters or instructions are provided to the agent to treat this external content as untrusted.
- Capability inventory: The skill implies the use of shell tools for conflict resolution and running project-specific commands like tests and formatters.
- Sanitization: There is no mention of sanitizing or escaping the content retrieved from PRs or issues.
- [COMMAND_EXECUTION]: The skill instructs the agent to "discover the project's automated checks and run them — typically typecheck, then tests, then format" (Step 4 in SKILL.md). Executing arbitrary code or scripts within a repository, especially one with conflicting changes from potentially untrusted contributors, carries a risk of executing malicious code embedded in the test suite.
Audit Metadata