bilingual-style-article-writer
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill interacts with the local file system strictly within its own subdirectories to store and retrieve style profiles and examples. This behavior is consistent with its intended use case for article generation.
- [PROMPT_INJECTION]: The skill ingests untrusted user data in the form of sample articles to create style profiles. 1. Ingestion points: User-provided sample articles mentioned in SKILL.md. 2. Boundary markers: None identified. 3. Capability inventory: File reading and writing within the references directory. 4. Sanitization: No sanitization steps are defined for the input samples.
- [NO_CODE]: No executable code or scripts were found in the provided files; the skill consists entirely of markdown templates and configuration logic.
Audit Metadata