resolve-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from conflicting files, commit messages, and external documentation, creating an attack surface for indirect prompt injection. \n
-
- Ingestion points: The agent reads conflict hunks, commit history, and PR/issue descriptions (SKILL.md steps 1 and 2). \n
-
- Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions embedded within the processed code or commit metadata. \n
-
- Capability inventory: The agent utilizes shell command execution for git operations and runs project-defined automated checks such as tests and typecheckers (SKILL.md steps 4 and 5). \n
-
- Sanitization: No sanitization or filtering of the external content is specified before the agent processes it. \n- [COMMAND_EXECUTION]: The skill requires the agent to execute several shell commands to modify the repository state and verify changes. \n
- Evidence: Instructs the use of
git commit,git rebase --continue, andgit cherry-pick --continueto finalize resolutions (SKILL.md step 5). \n - Evidence: Instructs the discovery and execution of project-specific automated checks like typecheckers, test suites, and formatters (SKILL.md step 4).
Audit Metadata