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