lfd-design
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.72). The skill’s runtime workflow ingests outsider-authored free text via the user-provided
goal.md/LOG.mdcontent and any “reference artifact” scraped/collected from public sources in Phase 0/3, which the agent then reads into its LLM context for planning and loss/eval design.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata