knowledge-auditor

Warn

Audited by Snyk on Feb 25, 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.md "Freshness Verification" step explicitly says it "compares knowledge entries against recently fetched research (e.g., from innovation-scout or google_web_search)" and the usage examples reference checking "the latest AWS blog updates," meaning the agent fetches and interprets public web content that can influence its auditing decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 11:56 AM