every-style-editor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (SAFE): No executable code, scripts (Python, JS, Shell), or package configuration files are present in the skill.
- [PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted user text for editing. Evidence Chain: 1. Ingestion points: External written content provided for review (SKILL.md). 2. Boundary markers: None specified; the skill does not use delimiters or instructions to ignore embedded commands in the input. 3. Capability inventory: None; the skill's operations are limited to generating text responses. 4. Sanitization: None, as the output is restricted to natural language feedback.
Audit Metadata