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, andGlobtools 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
TaskCreatebased 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