researching-libraries

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: 0.90). The skill's required workflow (INSTRUCTIONS.md and references/SEARCH-METHODS.md) instructs the agent to fetch and read public third-party sources (e.g., context7/get-library-docs, deepwiki read_wiki_contents, WebFetch calls to npms.io, bundlephobia, PyPI/crates.io/pkg.go.dev and GitHub) and to use that content to evaluate and decide on libraries, which could allow untrusted user-generated web content to influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 02:14 PM