style-modeler
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
normalize_style_frontmatter.py) included in the skill's package. This script is used for normalizing metadata in style files and does not perform network operations or unauthorized file access.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from external URLs (specifically WeChat articles). - Ingestion points: Data enters via the
web-article-extractortool called on user-supplied URLs inSKILL.md. - Boundary markers: None identified; the instructions direct the agent to analyze the extracted content in its entirety.
- Capability inventory: File write access to
.claude/styles/and execution of thenormalize_style_frontmatter.pyscript. - Sanitization: No explicit sanitization or filtering of the extracted article content is performed before the analysis phase.
Audit Metadata