resolve-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of Git commands (e.g.,
git status,git add,git merge --continue) and project-specific validation tools (tests, linters) to resolve conflicts and verify results. This is inherent to the skill's purpose and is managed through instructions that emphasize authorized integration and work protection.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Git conflict markers and project configuration files, which represents a potential surface for indirect prompt injection.\n - Ingestion points: Git conflict markers in source files,
git statusoutput, and project-specific test configurations in the target repository.\n - Boundary markers: The instructions do not define specific delimiters for untrusted content but advise the agent to inspect files for "accidental markers" and verify staged results against a baseline.\n
- Capability inventory: File system access, Git command execution, and execution of arbitrary project test suites.\n
- Sanitization: The skill mitigates risks by requiring the agent to manually verify diffs, check for accidental markers, and run existing test suites before completing any integration.\n- [EXTERNAL_DOWNLOADS]: The documentation references installation via
npx skills add SirDarcanos/agentskills, which fetches the skill from the vendor's repository. This is a standard installation pattern for the author's own resources.
Audit Metadata