blog-repurpose
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate content transformation and local file management within a defined scope (the 'repurposed/' directory).
- [INDIRECT_PROMPT_INJECTION]: The skill processes external blog content which could theoretically contain hidden instructions (Indirect Prompt Injection). However, the risk is minimal as the skill's primary actions are limited to text generation and file writing to a specific local path. Evidence:
- Ingestion points: Step 1 ('Read & Analyze') processes blog post content from the environment or user input.
- Boundary markers: Not explicitly defined in instructions, though the structured extraction in Step 1 serves as a natural filter.
- Capability inventory: File-system write operations ('repurposed/' directory).
- Sanitization: Not explicitly implemented, but the transformation into rigid templates for social media (Twitter, LinkedIn, etc.) limits the execution context of any injected instructions.
Audit Metadata