cold-outreach-sequence
Warn
Audited by Snyk on Apr 4, 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 required "Research tool calls" (e.g., web_search('[Company] [Name] news 2026'), web_search('[Person] LinkedIn') in SKILL.md and SKILL-OC.md) instruct the agent to fetch and ingest public web content and social media/LinkedIn posts and then use those signals to decide tiers and generate messaging, which clearly exposes the agent to untrusted third-party content that can influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata