code-explain

Warn

Audited by Snyk on Mar 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: 1.00). SKILL.md explicitly instructs the agent to "Lookup documentation for libraries/frameworks used (use WebSearch/WebFetch)" and SUBAGENT.md spawns a code-researcher to "Lookup documentation for libraries/frameworks used in {files}", which causes the agent to fetch and interpret public third-party web content that can influence its decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 12:55 AM