trail
Warn
Audited by Snyk on Nov 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read repository files and
.trail/learnings/written by teammates, which includes collaborator-authored content that could contain prompt injections.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill references an external npm package URL/locator via an instruction to run
npm install -g @trailhq/trail-code, constituting a common unofficial operational dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata