felo-twitter-writer
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill operates by executing local Node.js scripts from dependent skills (felo-superAgent, felo-x-search, felo-livedoc) to fetch tweets, manage documents, and interact with the SuperAgent API.\n- [PROMPT_INJECTION]: The skill processes untrusted data (tweets) which may contain instructions targeting the LLM. Ingestion points: External tweets are fetched using the felo-x-search skill scripts and included in the prompt. Boundary markers: The data is preceded by descriptive headers (e.g., 'Account bio:', 'Tweets:'), but lacks strong separators or instructions to ignore embedded commands. Capability inventory: The skill can execute local Node.js scripts and manage LiveDocs via subprocess calls. Sanitization: No content sanitization or filtering is applied to the retrieved tweets.
Audit Metadata