writing-skills

Warn

Audited by Snyk on Aug 26, 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). In testing-skills-with-subagents.md the runtime workflow explicitly has the agent run pressure scenarios and “document choices and rationalizations verbatim,” which uses outsider-authored scenario text supplied in the task prompt (e.g., the human’s “IMPORTANT: This is a real scenario. Choose and act.” blocks) without first selecting any trusted item.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 11:02 PM
Issues
1
Security Audit — snyk — writing-skills