tweet
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/typefully_scheduler.pyto interact with the Typefully API and uses thebirdCLI tool to fetch data from X/Twitter. - [INDIRECT_PROMPT_INJECTION]: The skill processes external tweet data to calibrate the agent's voice, creating a potential vector for malicious instructions to enter the agent's context.
- Ingestion points: External content is fetched using the
bird searchcommand as described inSKILL.md. - Boundary markers: The skill does not define specific delimiters to isolate external tweet content from its internal instructions.
- Capability inventory: The agent can execute local scripts and perform authenticated network requests to a social media management API.
- Sanitization: No explicit sanitization or filtering of the retrieved tweet content is performed before processing.
Audit Metadata