writing-style
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): The skill contains stylistic constraints and persona-steering instructions. While it uses high-priority flags ('priority: root', 'always_invoke: true'), these are used to ensure stylistic consistency and do not attempt to bypass safety filters or extract system prompts.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or network communication commands (e.g., curl, wget) were detected.
- Obfuscation (SAFE): All content is provided in clear-text markdown. There is no evidence of Base64 encoding, zero-width characters, or homoglyph-based obfuscation.
- Unverifiable Dependencies & RCE (SAFE): The skill does not reference or install any external Python or Node.js packages. No remote script execution patterns are present.
- Indirect Prompt Injection (INFO): The skill processes user-initiated writing tasks to apply styles.
- Ingestion points: Data enters via user prompts for 'all writing tasks'.
- Boundary markers: None (instructions are applied globally).
- Capability inventory: No capabilities for command execution, file writing, or network access.
- Sanitization: Not applicable as there are no side-effect capabilities. The severity is negligible (INFO).
Audit Metadata