setperms

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). This skill explicitly enables and instructs web fetching of arbitrary public content — the .claude/rules/cli-tools.md "Web Fetching" section plus the permissions list authorize tools like WebFetch, r.jina.ai/URL, firecrawl, curl/httpie and Perplexity/gemini CLI to retrieve and be read/processed from third‑party websites.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:43 AM