bird
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
birdCLI from third-party sources (NPM package@steipete/birdand Homebrew tapsteipete/tap/bird). These are external dependencies not directly managed by the skill author. - [DATA_EXFILTRATION]: To function, the tool accesses sensitive browser profile data and cookie databases (e.g., via the
--chrome-profile-dirflag) to retrieve authentication tokens for X/Twitter. - [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the system and network, including posting updates and uploading media files from the local filesystem.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from an external social media platform.
- Ingestion points: Untrusted data enters the agent's context through commands like
bird read,bird home, andbird searchas defined inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit directives to ignore instructions embedded within the retrieved tweet content.
- Capability inventory: The skill provides write-access tools such as
bird tweet,bird reply, andbird follow(documented inSKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the external source.
Audit Metadata