resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to process potentially untrusted external data during conflict resolution, creating a surface for indirect prompt injection.
- Ingestion points:
SKILL.md(Step 2) instructs the agent to read commit messages, pull request content, and issue/ticket descriptions. - Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore embedded instructions within external metadata.
- Capability inventory: The skill instructions (Steps 4 and 5) involve executing git commands and running arbitrary project-defined automated checks such as tests and typecheckers.
- Sanitization: Absent; the skill does not specify any validation or filtering of the external data before it is ingested.
Audit Metadata