hugo-write-post
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local Python script
scripts/analyze_style.pyand uses standard Hugo CLI commands (hugo new,hugo server) to manage content. All operations are local to the repository. - [PROMPT_INJECTION]: Susceptible to Indirect Prompt Injection (Category 8) as it reads user-provided blog posts to capture writing style. Malicious instructions in these posts could affect agent behavior.
- Ingestion points: Markdown files in the
content/directory. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading posts.
- Capability inventory: Local command execution, file system writing, and local server hosting.
- Sanitization: Content from existing posts is processed without sanitization.
Audit Metadata