test-review

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of reading and analyzing untrusted source and test code. \n
  • Ingestion points: The skill's Explore sub-agents are instructed to read every source and test file within the provided module and test paths. \n
  • Boundary markers: The prompts for sub-agents lack explicit delimiters or warnings to disregard instructions found within code comments or documentation. \n
  • Capability inventory: The skill utilizes cat, Glob, and Task (sub-agent) tools to read filesystem data and process it through LLMs. \n
  • Sanitization: No sanitization or filtering of the ingested file content is performed prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:35 AM