filebrowser-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows and expects plaintext passwords in skillconfig.json and as command-line arguments (e.g., --password ), which would require the agent to embed secret values verbatim in generated commands or config, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime workflows (e.g., scripts/directory_sync.py and upload_and_share.py plus references/search-service.md) explicitly fetch and ingest remote, user-controlled content and metadata from arbitrary FileBrowser instance URLs (GET /api/resources, /api/raw, /api/search and public /api/public/* endpoints), and those remote results (search hits, file metadata and file contents) are used to decide uploads/downloads and other actions, exposing the agent to untrusted third‑party content that could influence behavior.