write-well
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of text-based instructions and guidelines for prose writing and editing. It does not include any executable code, scripts, or configuration files that could interact with the host system.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or external downloads were detected. The 'Attribution' section mentions GitHub repositories as sources of inspiration, but these are not cited as active dependencies or download targets.
- [DATA_EXFILTRATION]: There are no network-related commands (e.g., curl, wget) or file system operations that could lead to data exfiltration or unauthorized file access.
- [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters or override system instructions.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found in the provided files.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided text for 'improvement,' it lacks any dangerous capabilities (such as shell execution or network access) that could be exploited via indirect prompt injection.
Audit Metadata