fabric-council
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The runtime workflow feeds the outsider-authored free text
π.taskinto the LLM via theagent(...)prompts (and again during synthesis), sinceπ.taskis not shown as user-authored in SKILL.md and may originate from external/third-party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata