blog-post
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard content creation workflow for blog posts. It includes directory specifications, naming conventions, and frontmatter templates. No dangerous commands, network exfiltration, or obfuscation techniques were found.
- [PROMPT_INJECTION]: The skill processes untrusted user input to create MDX files, which represents a surface for indirect prompt injection. However, the risk is minimal as it involves writing static content files without execution context. 1. Ingestion points: User-provided content, brain dumps, and outlines. 2. Boundary markers: None present. 3. Capability inventory: Local file creation in src/data/posts/ using available file system tools. 4. Sanitization: Limited to typo correction and header formatting.
Audit Metadata