skill-update

Warn

Audited by Snyk on Feb 26, 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). This skill's Step 4 "Optional Web Research" instructs the agent to use a Task tool with an Explore subagent to search the open web for "best practices" and return findings to inform planning changes, which clearly fetches and interprets untrusted third-party web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 08:33 PM