x-bookmarks
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt includes examples that pass secrets verbatim on the command line or inline (e.g., --client-secret "YOUR_SECRET", X_API_BEARER_TOKEN="your_token"), which would encourage the agent to accept and emit actual secret values in generated commands — an explicit exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill fetches and processes user-saved tweets (user-generated, untrusted content) via bird CLI (e.g.,
bird bookmarks --jsonin fetch_bookmarks.sh / SKILL.md) or the X API v2 endpoint (https://api.x.com/2/users/{id}/bookmarksin scripts/fetch_bookmarks_api.py), and the agent is explicitly expected to read, summarize, categorize, and act on that content as part of its workflow, allowing indirect prompt injection via third-party tweets.
Audit Metadata