add-sfx

Warn

Audited by Snyk on Jun 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). The required runtime workflow calls sfx_search/sfx_pull, which (via the Woven SFX MCP server) will fetch and ingest catalog/search results and then download the selected .wav metadata/paths into the agent context; this is outsider-sourced public CDN content (https://sfx.woven.video/catalog.json and related catalog entries) that the user did not author.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill requires running an MCP server via "npx -y woven-sfx-mcp" and its runtime scripts fetch and execute remote content from the Woven CDN (e.g., https://sfx.woven.video/catalog.json), so external code/content is downloaded and executed during runtime.

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
Jun 29, 2026, 03:19 AM
Issues
2
Security Audit — snyk — add-sfx