code-smell-validator
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md Phase 1 "Gather Environmental Context (Optional)" step explicitly instructs the agent to query external MCP plugins (e.g., GitHub issues, public docs/ADRs) and "Summarize external signals and how they might influence severity," meaning the agent would ingest untrusted, user-generated third-party content that can change its severity assessments and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata