agent-development

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). The skill explicitly recommends allowlisting WebFetch(domain:*) in .claude/settings.json (see the "Allowlist Pattern" in SKILL.md and the allowlist examples in rules/custom-agent-instructions.md), and several prompts instruct agents to "verify with external check
  • npm view, API call, etc.", which enables agents to fetch and read arbitrary public web domains (untrusted third‑party content) as part of their workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 10:27 PM