Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md shows it reads and searches X/Twitter content (e.g., "bird read ", "bird thread", "bird search") — untrusted, user-generated posts from the public web — and also supports actions (tweet/reply/follow) so third-party content could materially influence subsequent agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata