content-sanitization

Warn

Audited by Snyk on May 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly says the skill processes WebFetch/WebSearch results, GitHub (gh) outputs, and user-provided URLs and notes an automated PostToolUse hook (sanitize_external_content.py) that sanitizes outputs from WebFetch/WebSearch and gh/curl, so the agent will ingest untrusted public web/GitHub/user-provided content that could contain indirect prompt injections.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 07:37 AM
Issues
1