feature-spike
Warn
Audited by Snyk on Jul 31, 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 skill “Feature Spike” routes user-provided prompts (free text) into the required runtime workflow via
default_prompt, which instructs the agent to produce a bounded probe and decision evidence, so outsider-authored text is directly ingested by the LLM at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata