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 --json in fetch_bookmarks.sh / SKILL.md) or the X API v2 endpoint (https://api.x.com/2/users/{id}/bookmarks in 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
Risk Level
HIGH
Analyzed
Feb 16, 2026, 09:46 AM