social-media-content-repurposer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are strictly focused on content analysis and platform-specific formatting. There are no attempts to override agent safety protocols or system prompts.
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process untrusted external data (blog posts, articles).
- Ingestion points: Instructions refer to 'Analyze Source Content' and 'repurpose this blog post'.
- Boundary markers: Absent; there are no specific delimiters used to wrap the input content.
- Capability inventory: None; the skill does not possess capabilities for file writing, network requests, or command execution.
- Sanitization: Absent; the skill relies on the underlying LLM's inherent safety filters.
- [Data Exposure & Exfiltration] (SAFE): No references to sensitive local paths (~/.ssh, ~/.aws) or commands capable of exfiltrating data (curl, wget) were found.
- [Remote Code Execution] (SAFE): The skill does not include any scripts or commands to download or execute remote code.
- [Obfuscation] (SAFE): No encoded strings, zero-width characters, or homoglyphs were detected in the markdown or metadata.
Audit Metadata