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