local-counsel-manager-scott-margetts
Warn
Audited by Snyk on Jun 26, 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). The skill’s Mode 4 runtime path ingests outsider-authored free text when the user pastes an email from a local counsel contact (explicitly treated as incoming LC correspondence via the
[FROM LC]tag), and that email body is then used to generate the scope response letter in the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata