social-post-writer
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected.
- [SAFE]: The skill uses designated tools (e.g., get_marketing_context, search_content) to interact with its environment, which is consistent with the provided vendor context ('timescale' / 'Tiger Den').
- [SAFE]: The skill demonstrates safe data handling by enforcing a 'No Fly List' check, ensuring restricted customer information is not publicly disclosed.
- [SAFE]: The skill has an indirect prompt injection surface when repurposing external content. Ingestion points: User-provided URLs and text (SKILL.md). Boundary markers: Absent. Capability inventory: Social media text generation. Sanitization: Brand voice and AI slop checks. The risk is considered safe given the limited output scope.
Audit Metadata