prune-tests
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to perform its duties, including a local utility script (
../sweep/scripts/known-work.sh) and the repository's own test runner and coverage tools. These operations are restricted to the local environment and are necessary for the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes content from the repository, which could potentially contain malicious instructions intended to influence the agent's behavior during the audit phase.
- Ingestion points: The agent reads repo-level configuration (
AGENTS.md,CLAUDE.md) and the source code of all test files in the targeted area during the audit step. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these files.
- Capability inventory: The agent possesses capabilities to modify or delete files, execute shell scripts and test runners, perform git operations (fetch, branch, push, PR), and spawn sub-agents for parallel auditing.
- Sanitization: The instructions do not define sanitization or validation steps for the content of the analyzed test files before they are processed by the agent.
Audit Metadata