social-writer
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a text-based instructional prompt designed for content creation. It does not contain executable code, system commands, or network operations.
- [DATA_EXPOSURE]: The skill requests access to
MEMORY.mdandUSER.mdto provide context-aware responses regarding company strategy and user preferences. This is standard behavior for personalized AI assistants and no exfiltration logic is present. - [PROMPT_INJECTION]: No patterns associated with instruction overrides, safety filter bypasses, or system prompt extraction were found.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any remote package installations or script executions. The URL provided in
SOURCE.mdis for attribution and documentation purposes.
Audit Metadata