test-co-location-enforcer

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell commands (find, mv, rm -rf) to help reorganize test files and delete the legacy __tests__/ directories. These commands are restricted to the project scope (e.g., src/__tests__/) and are consistent with the skill's stated purpose of enforcing file structure standards.
  • [INDIRECT_PROMPT_INJECTION]: The skill audits directory structures and file names to find migration targets. This introduces a vulnerability surface where a malicious actor could name files or directories in a way that attempts to influence the agent's behavior during the audit process.
  • Ingestion points: File system paths and names returned by the find commands in SKILL.md.
  • Boundary markers: None specified in the instructions for processing the file list.
  • Capability inventory: File movement (mv), directory deletion (rm -rf), and file searching (find) as described in the migration workflow.
  • Sanitization: No explicit sanitization or validation of the discovered file paths is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 03:29 PM