jmb-resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which can contain malicious instructions. * Ingestion points: Reads conflicting files, git history, commit messages, PRs, and issues (SKILL.md, steps 1-2). * Boundary markers: No delimiters or instructions to ignore embedded commands are specified. * Capability inventory: The agent is instructed to discover and run automated checks (tests, formatters) and execute git commands (stage, commit) (SKILL.md, steps 4-5). * Sanitization: No evidence of validation or sanitization of ingested content before processing.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to resolve conflicts and run project checks. * Evidence: Steps 4 and 5 in SKILL.md involve running automated checks and git operations.
Audit Metadata