every-style-editor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is composed entirely of markdown instructions. There are no scripts (.py, .js, .sh), executables, or configuration files provided.
- [DATA_EXFILTRATION] (SAFE): There are no commands or network operations (e.g., curl, fetch) that could exfiltrate data. The skill only references a local documentation file for style rules.
- [PROMPT_INJECTION] (SAFE): No patterns of prompt injection, jailbreaking, or instruction-overriding were detected in the skill text.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill is intended to process untrusted user content (articles for review), it possesses zero exploitable capabilities. There is no code execution, file system writing, or network access that could be triggered by malicious content in the text being edited. Evidence: 1. Ingestion points: User-provided text for editing. 2. Boundary markers: Not explicitly defined. 3. Capability inventory: None. 4. Sanitization: Not applicable as there are no downstream actions.
Audit Metadata