fix-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection.
- Ingestion points: The skill reads conflicting file content and Git status metadata to identify and resolve merges (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings for the code being processed.
- Capability inventory: The agent is authorized to write to files (resolve conflicts) and execute shell commands for compilation, linting, and testing (SKILL.md).
- Sanitization: There are no explicit steps to sanitize or validate the content of the code before it is used to influence the resolution process or executed during tests.
- [COMMAND_EXECUTION]: The skill directs the agent to execute workspace-specific commands for building and testing code. This allows the execution of code defined in the project, which poses a risk if the code has been maliciously altered in the branch being merged.
Audit Metadata