discovering-abstract-portal
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly instructs the agent to perform live reads from the Portal (e.g., agw portal apps list, agw portal streams list, agw portal user-profile get), which fetch untrusted/user-generated app streams and profiles that the agent is expected to read and could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata