brand-voice
Warn
Audited by Snyk on Nov 21, 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 required workflow reads recent X posts via
x-api(SKILL.md:34), which the agent actively fetches, so any outsider-authored text it contains is only exposed if the agent selects or pulls that content, not because outsiders can push into a monitored queue.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata