unit-test
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes commands defined in repository files such as package.json, Makefiles, and other task runners. This capability relies on the integrity of the workspace configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository-level files like AGENTS.md, CONTEXT.md, and task specifications to determine its execution logic.
- Ingestion points: Processes AGENTS.md, CONTEXT.md, task specifications, and repository test documentation.
- Boundary markers: No explicit boundary delimiters are defined to prevent instructions in these files from influencing the agent.
- Capability inventory: Execution of shell commands for unit testing.
- Sanitization: No explicit sanitization of command strings derived from repository configuration is documented.
Audit Metadata