doc-utest-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its primary function is to ingest and process external data (UTEST artifacts) which could contain malicious instructions.
  • Ingestion points: The skill reviews UTEST content quality and consistency (referenced in SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested data.
  • Capability inventory: The skill is designed to produce markdown reports; no dangerous capabilities like code execution or network access are specified.
  • Sanitization: No sanitization or filtering of input data is mentioned.
  • [NO_CODE]: The skill does not provide any executable scripts. It consists of markdown instructions and a single file containing a file path string. This limits the attack surface to the logic of the prompt itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:13 PM