meta-searching

Warn

Audited by Snyk on Mar 6, 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). The skill's SKILL.md explicitly instructs the agent to perform "Direct URL Extraction" and to extract/summarize content from public websites and repositories (e.g., "https://docs.anthropic.com/en/docs/claude-code" and "https://github.com/example/repo"), meaning it fetches and interprets untrusted third-party web content as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary external content at runtime (e.g., https://github.com/example/repo) and injects that content into the agent context for extraction/summarization, so remote files can directly control prompts fed to the model.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 10:46 AM