workspace
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of arbitrary shell commands through the management of repository tasks and git operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the local repository (e.g., Taskfiles, git logs, and file paths).
- Ingestion points: The arguments for task_run, find_test, and test_triage.
- Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore instructions embedded within the processed repository data.
- Capability inventory: The skill can execute shell commands via the task_run function and perform git operations.
- Sanitization: No mechanisms for sanitizing or validating repository content or user-provided arguments are described.
Audit Metadata