bird-twitter-moderation
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local binaries located in the user's home directory, specifically
$HOME/Projects/bird/birdand$HOME/.openclaw/bin/bird-gui, to perform data retrieval and account moderation actions. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it fetches and processes untrusted content from X (Twitter).
- Ingestion points: Data enters the agent's context through the output of commands like
$HOME/Projects/bird/bird read TWEET_IDand$HOME/Projects/bird/bird thread TWEET_ID. - Boundary markers: There are no instructions providing delimiters or warnings to ignore embedded instructions within the fetched tweets.
- Capability inventory: The skill provides the agent with the ability to perform impactful actions such as
blockandmutebased on the content it reviews. - Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the external content before the agent evaluates it.
Audit Metadata