write-spec

Warn

Audited by Snyk on Jul 19, 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). SKILL.md’s required workflow includes “Research” and “Capture the discovered source/repo/article/paper links… and turn any exemplar into a reproduction spike,” which at runtime can involve fetching/reading outsider-authored web pages or external repos/articles and feeding their free text into the agent’s LLM context.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 19, 2026, 11:46 PM
Issues
1
Security Audit — snyk — write-spec