stale-labels
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime the skill calls Linear MCP tools (e.g.,
mcp__claude_ai_Linear__list_issuesin Step 4) that return outsider-authored free text like issuetitles; those titles are then passed back into the agent’s LLM context and rendered in the report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata