skill-lookup

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill fetches and retrieves user-contributed skills from the public prompts.chat registry using search_skills/get_skill and reads SKILL.md and other returned files, exposing the agent to untrusted, user-generated third‑party content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 10:20 PM