style-extract
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs routine file system operations such as creating directories and writing/reading JSON files within the
./writing-workspace/styles/path. These operations are aligned with the skill's stated purpose of managing a style library. - [DATA_EXFILTRATION]: There are no network operations, such as
curl,wget, or API calls, detected in the instructions. Data remains confined to the local workspace. - [PROMPT_INJECTION]: The skill does not contain instructions attempting to bypass safety filters or override the agent's core behavioral constraints.
- [REMOTE_CODE_EXECUTION]: No external scripts are downloaded or executed. The skill does not use
eval,exec, or similar dynamic execution functions. - [SAFE]: The skill processes user-provided articles to extract stylistic metadata. While this represents a surface for Indirect Prompt Injection, the instructions strictly define the extraction dimensions (e.g., vocabulary level, sentence rhythm), which forces the agent to treat the input as data to be analyzed rather than instructions to be followed.
Audit Metadata