resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to identify and execute local automated checks, including type checkers, tests, and formatting tools found within the project repository.
- [PROMPT_INJECTION]: The agent is directed to ingest data from external sources such as commit messages, pull request descriptions, and issue trackers to understand code changes. This creates a surface for indirect prompt injection where untrusted text could influence agent actions.
- Ingestion points: Git commit history, pull request metadata, and issue tracker content (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions found within the processed metadata.
- Capability inventory: The skill allows the agent to modify the codebase through conflict resolution, stage files, commit changes, and execute local scripts (automated checks).
- Sanitization: There is no mention of sanitization or filtering of the content retrieved from external repository sources.
Audit Metadata