test-guide

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (application source code and test files) which may contain instructions that could influence the agent's auditing decisions.
  • Ingestion points: The skill instructs the agent to read all test files and production code in 'Phase 2: Explore, Count & Classify'.
  • Boundary markers: There are no instructions provided to treat the content of the analyzed files as data only or to ignore embedded natural language instructions within comments or string literals.
  • Capability inventory: The skill has the capability to delete files ('Report + Delete') and write new code ('Scaffold') based on its analysis.
  • Sanitization: No sanitization or filtering of the ingested code content is specified before the agent performs its classification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:35 AM