knowledge-review

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to read and process external documents ('knowledge artifacts') provided by users or external sources.
  • Ingestion points: The skill uses Read, Grep, and Glob tools to ingest content from knowledge reports, courses, or strategy documents (referenced in SKILL.md).
  • Boundary markers: There are no instructions to the agent to use delimiters or ignore embedded instructions within the artifacts it reads.
  • Capability inventory: The skill has the capability to read any file accessible to the agent and create tasks using TaskCreate based on the content of the artifacts.
  • Sanitization: No validation or sanitization of the artifact content is performed before the agent processes it for quality review.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 08:38 AM