Bird

Fail

Audited by Snyk on Feb 28, 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 documents and exposes command-line flags (--auth-token, --ct0) that instruct users (or an agent) to pass cookie/auth tokens directly on the command line, which would require the LLM to include secret values verbatim in generated commands—an high-risk secret-exfiltration pattern.

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows the tool fetching and interpreting public X/Twitter content (e.g., "Reading Tweets" commands like bird read <url-or-id>, bird thread, bird search) — user-generated, untrusted social-media content that the agent reads and can influence subsequent actions (e.g., tweet, reply, follow), exposing it to indirect prompt-injection risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 28, 2026, 05:57 PM