refine-review

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface detected. The skill is designed to analyze external PBI artifacts which may contain instructions intended to influence the agent's behavior. \n
  • Ingestion points: PBI artifacts located in team-artifacts/pbis/ (referenced in SKILL.md). \n
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands within the ingested PBI content. \n
  • Capability inventory: The skill utilizes TaskCreate for task management and has the ability to read project files and write reports to plans/reports/. \n
  • Sanitization: Absent; there is no mention of sanitization, escaping, or validation of the content processed from external artifacts. \n- [NO_CODE]: The skill consists exclusively of markdown-based instructions and workflows; it does not include executable scripts, binaries, or automated code logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 06:41 AM