bird

Warn

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install an external CLI tool from third-party sources not included in the trusted vendors list, specifically @steipete/bird via NPM and steipete/tap/bird via Homebrew.\n- [REMOTE_CODE_EXECUTION]: The documentation includes instructions to execute remote code directly from the NPM registry using the bunx command, which downloads and runs the @steipete/bird package without a persistent installation.\n- [COMMAND_EXECUTION]: The skill primarily operates by executing the bird command-line binary to perform account actions and read data.\n- [DATA_EXFILTRATION]: The tool is designed to access highly sensitive local data, including browser cookie databases and profile directories (e.g., --chrome-profile-dir, --cookie-source), and reads configuration from ~/.config/bird/config.json5. These credentials are used to authenticate requests to external servers.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted content from X/Twitter.\n
  • Ingestion points: Untrusted data enters the agent context through commands like bird read, bird search, bird home, and bird mentions.\n
  • Boundary markers: There are no instructions or delimiters defined to separate the external social media content from the agent's internal logic.\n
  • Capability inventory: The skill possesses state-changing capabilities, including bird tweet, bird reply, bird follow, and bird unfollow, which could be exploited via injection.\n
  • Sanitization: The skill does not mention any sanitization, filtering, or validation of the content fetched from X/Twitter.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 09:12 PM