doc-itest-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to process untrusted ITEST artifacts, which introduces a potential surface for indirect prompt injection.\n
  • Ingestion points: Integration test (ITEST) artifacts and implementation plans provided as external input (referenced in SKILL.md).\n
  • Boundary markers: None identified; the instructions do not define delimiters or specific 'ignore embedded instructions' directives for the source material.\n
  • Capability inventory: The skill generates review reports and writes them to the local file system using a specific naming convention (ITEST-NN.R_review_report_vNNN.md).\n
  • Sanitization: No sanitization, escaping, or validation of the input content is described in the provided guidelines.\n- [NO_CODE]: The provided files consist of markdown instructions, metadata, and a file path reference. No executable scripts, source code, or binary files were included in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 12:13 PM