prompt-architect
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's mandatory Step 1 ("Ingest and Analyze") explicitly instructs the agent to "Links: Browse or infer context to extract key information," which requires fetching and interpreting arbitrary third-party URLs as part of its core workflow, allowing untrusted web content to influence prompt-generation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata