capability-trainer

Warn

Audited by Snyk on Mar 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to "Use web_search for official docs" in the Quick Learning process and to "Collect resources" (official docs, tutorials) with external "Reference links", so the skill fetches and ingests public web/tutorial content that the agent is expected to read and act on.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 02:52 AM