writing-style
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No instructions attempt to override agent safety or extract system prompts.
- Data Exposure & Exfiltration (SAFE): No sensitive data access or network transmission commands are present.
- Obfuscation (SAFE): No encoded content or hidden characters were detected.
- Unverifiable Dependencies & RCE (SAFE): The skill contains no code or external package references.
- Indirect Prompt Injection (LOW): While the skill processes untrusted text input, it lacks the functional capabilities (e.g., shell access, file writing, network calls) necessary to facilitate an attack. Evidence: 1. Ingestion: Processes text for editing in SKILL.md. 2. Boundaries: Absent. 3. Capabilities: None (no code or tool definitions). 4. Sanitization: Absent.
Audit Metadata