review-artifact

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for Indirect Prompt Injection. The skill is designed to ingest and analyze untrusted content such as PBIs, design specifications, and user stories.
  • Ingestion points: External artifact descriptions and specifications (SKILL.md).
  • Boundary markers: None found; there are no instructions to isolate artifact content from the agent's control logic.
  • Capability inventory: Access to tool TaskCreate for process automation and the ability to spawn code-reviewer sub-agents for parallel processing.
  • Sanitization: No input validation or filtering is specified for the content of the artifacts being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM