content-research-writer
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for collaborative writing, outlining, and research. No patterns associated with prompt injection, credential theft, or unauthorized data access were found.
- [COMMAND_EXECUTION]: The skill documentation includes benign example shell commands (
mkdir,touch) for local file management by the user. These do not involve administrative privileges or dangerous execution patterns. - [PROMPT_INJECTION]: The 'Conduct Research' feature involves the agent fetching and processing external information from the web. While this represents a surface for indirect prompt injection, the skill's instructions focus on content extraction and citation management without providing capabilities for exfiltration or privilege escalation.
Audit Metadata