resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by requiring the agent to analyze external, user-controlled metadata to determine the intent of code changes.
- Ingestion points: The agent is instructed to read commit messages, PR descriptions, and issue/ticket content (SKILL.md).
- Boundary markers: Absent. No delimiters or instructions are provided to help the agent distinguish between legitimate context and potentially malicious instructions embedded in the metadata.
- Capability inventory: The skill allows the agent to execute project-specific automated checks (typecheck, tests, format) and git commands (SKILL.md).
- Sanitization: Absent. The skill does not include any steps to validate or sanitize the external data before processing it.
Audit Metadata