blog-audit
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (analyze_blog.py) to perform the core audit logic. The script location is resolved using a relative path from the skill directory.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external blog content and project configuration files, which could contain malicious instructions.
- Ingestion points: Recursively scans markdown and HTML files across various blog-related directories (e.g., content/, posts/, blog/).
- Boundary markers: Utilizes a fenced helper and an Untrusted-Data Contract for project-level files.
- Capability inventory: Executes shell commands via python3 and performs file system writes to create reports under the reports/ directory.
- Sanitization: Explicitly instructs the agent to treat all post content, frontmatter, and comments as data rather than instructions, and to ignore any directives found within those files.
Audit Metadata