self-improve-with-tinyfish
Warn
Audited by Snyk on Sep 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to actively search and fetch arbitrary URLs from web sources and documentation using TinyFish, which represents low-risk ingestion of external content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata