resolving-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow that involves ingesting untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: Steps 1 and 2 in
SKILL.mddirect the agent to read git history, commit messages, pull request content, and issue/ticket descriptions. - Boundary markers: The instructions lack specific delimiters or warnings to prevent the agent from following instructions embedded within the git metadata or external descriptions.
- Capability inventory: The agent is authorized to run automated checks (typecheck, tests, format) and perform git operations (stage, commit) as seen in
SKILL.mdsteps 4 and 5. - Sanitization: There are no instructions for the agent to sanitize or validate the external content before processing it.
- [COMMAND_EXECUTION]: The skill instructs the agent to discover and run automated project checks which involves executing repository-defined code.
- Evidence: Step 4 in
SKILL.mdexplicitly tells the agent to run "typecheck, then tests, then format." This involves executing binaries or scripts located within the repository being merged, which could lead to arbitrary command execution if the repository contains malicious configuration files.
Audit Metadata