social-content
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional frameworks for social media writing and does not involve executable code, external downloads, or sensitive file access.
- [PROMPT_INJECTION]: The skill is designed to ingest user-provided content for transformation and repurposing, which is a surface for indirect prompt injection. However, the risk is negligible because the skill does not use any tools with network or system-writing capabilities.
- Ingestion points: User-provided text for repurposing tasks.
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the skill body.
- Capability inventory: The skill has no access to the file system, network, or shell.
- Sanitization: No input sanitization is performed.
Audit Metadata