resolving-merge-conflicts
Warn
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to "Discover the project's automated checks and run them — typically typecheck, then tests, then format." This pattern involves identifying and executing arbitrary shell commands defined in local project files (e.g., package.json, Makefile, or CI configs). If a repository contains malicious test or build scripts, the agent will execute them with the user's local permissions.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted external data.
- Ingestion points: The agent reads "commit messages", "PRs", and "original issues/tickets" (SKILL.md).
- Boundary markers: None provided; the agent reads this data directly into context without delimiters or instructions to ignore embedded commands.
- Capability inventory: The agent has the capability to run subprocesses and shell commands to perform "automated checks" (SKILL.md).
- Sanitization: There is no evidence of sanitization or filtering for the content retrieved from PRs or issues.
Audit Metadata