kirito-writing-style
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): The instructions strictly define a writing persona and style. There are no attempts to bypass safety filters or override system instructions.
- DATA_EXFILTRATION (SAFE): No network commands (curl, wget) or sensitive file path references are present.
- REMOTE_CODE_EXECUTION (SAFE): The skill contains no executable scripts or commands. It is entirely composed of Markdown text.
- CREDENTIALS_UNSAFE (SAFE): No hardcoded API keys, tokens, or secrets were found.
- INDIRECT_PROMPT_INJECTION (INFO):
- Ingestion points: The skill is designed to process external technical content (articles/tutorials) as input for rewriting.
- Boundary markers: Absent.
- Capability inventory: None. The skill only performs text transformation and does not have access to subprocesses, file-system writes, or network requests.
- Sanitization: Absent.
- Severity: INFO. While it processes untrusted data, the lack of side-effect capabilities makes the risk negligible.
Audit Metadata