tweet-writer
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of Markdown-based instructions and contains no code, scripts, or binary payloads.
- [SAFE]: There are no hardcoded credentials or requests to access sensitive files or system resources.
- [PROMPT_INJECTION]: The research phase (Phase 1) directs the agent to gather examples via web search, which constitutes an indirect prompt injection surface. The skill does not provide boundary markers or sanitization instructions for this ingested data, but the risk is rated as safe given that the agent's only capability is creative text generation.
- [SAFE]: All external URLs point to well-known social media marketing and copywriting resources.
Audit Metadata