conflicts
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code content found within merge conflict markers. * Ingestion points: Local file content during git conflict resolution. * Boundary markers: Absent; the instructions do not specify a delimiter or warning to ignore instructions embedded within the code being resolved. * Capability inventory: Implicit file writing and execution of git commands (merge/rebase). * Sanitization: None.
Audit Metadata