content-research-writer
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and examples related to research and writing. No malicious code, command injection, or obfuscated patterns were detected.
- [COMMAND_EXECUTION]: The skill includes documentation for standard file system operations (e.g.,
mkdir,touch) to guide the user in setting up a local project workspace. These are benign and appropriate for the skill's intended use case. - [PROMPT_INJECTION]: The instructions focus on persona adoption for writing assistance and do not contain attempts to override agent safety protocols or bypass constraints.
- [DATA_EXPOSURE]: The skill defines a local file structure for user drafts but does not attempt to access or exfiltrate sensitive system configuration files or credentials.
Audit Metadata