iblai-api-agent-safety
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow performs runtime GET requests to an external API to load moderation/safety prompts and responses (outsider-authored free text from the API) into the agent’s context via the “Reads” endpoints.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata