goalflow
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The agent’s required runtime workflow injects Markdown bodies from goalflow runtime
skills/<id>/SKILL.mdinto the system prompt after LLM-based skill matching (“load bodies → inject into prompt”), so outsider-authored free text in SKILL bodies can be ingested at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata