terse-improve
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). This skill’s required workflow repeatedly instructs the user to fetch and replay production run history and test sample events via the
terse history/terse test list/terse replaycommands (outsider-authored prior agent outputs + trigger payloads stored on the backend), which the agent then uses as LLM-readable event context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata