every-style-editor-2
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): No executable code, scripts, or binary files were found within the skill. The logic is entirely contained within the natural language instructions of the markdown file.
- PROMPT_INJECTION (LOW): The skill is designed to process untrusted external data (articles, newsletters, and documentation), which creates a surface for Indirect Prompt Injection.
- Ingestion points: User-provided text content (articles, blog posts, newsletters, etc.).
- Boundary markers: None present. The instructions do not define delimiters for user input or warn the agent to ignore instructions embedded in the text.
- Capability inventory: None. The agent has no access to tools, network operations, or file system modifications.
- Sanitization: None present.
- Assessment: Although susceptible to instructions embedded in the analyzed text, the lack of any functional capabilities (scripts/tools) means the agent cannot be used to perform malicious actions beyond generating incorrect text output.
Audit Metadata