agentic-code-reasoner

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: 0.90). The skill's SKILL.md (Phase 2) explicitly instructs the agent to "use grep_search or web_fetch to find the documentation or implementation," which requires fetching and interpreting open/public web documentation/implementations (untrusted third-party content) that can materially influence the agent's reasoning and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 08:45 AM