light-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions are consistent with its stated purpose of resolving git conflicts. No malicious commands or suspicious behaviors were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it reads commit messages, PRs, and issues (ingestion points in SKILL.md). No explicit boundary markers or sanitization steps are defined to isolate this untrusted content. However, the available capabilities are restricted to local git operations and project-defined automated checks (capability inventory in SKILL.md), which represents a low-risk profile inherent to development tools.
Audit Metadata