skills/un-seen/hedwigai-skills/cited-web-research/Snyk

cited-web-research

Warn

Audited by Snyk on Oct 14, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (low risk: 0.10). The agent actively searches and fetches arbitrary web pages and search results via browser and search tools.

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

Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation of a remote plugin/MCP server from arbitrary URLs (https://claude.ai/directory/hedwigai, https://mcp.hedwigai.com/, and un-seen/hedwigai-skills), which constitutes an unverifiable runtime external dependency with unknown third-party publisher provenance.

Issues (2)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 14, 2026, 10:59 AM

Issues

2