content-research-writer
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in this skill.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override safety guidelines, extract system prompts, or bypass agent constraints. The focus is entirely on content creation and writer collaboration.
- [DATA_EXFILTRATION]: No sensitive file paths (such as .ssh or .aws) are accessed. The skill suggests a benign local directory structure in the user's home folder (~/writing/) for document management.
- [COMMAND_EXECUTION]: The shell commands provided in the documentation (mkdir, cd, touch) are standard utilities for file and directory management and do not pose a security risk in this context.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified dependencies.
- [OBFUSCATION]: The skill uses clear, human-readable markdown and instructions with no hidden characters, Base64 encoding, or other obfuscation techniques.
Audit Metadata