agentlens
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for using documentation-based navigation patterns. It does not contain any executable code or instructions that bypass safety filters.
- [COMMAND_EXECUTION]: The documentation suggests using a local
agentlenscommand to regenerate stale documentation. This refers to a CLI tool assumed to be part of the user's environment and does not involve remote script execution or unauthorized command injection. - [DATA_EXFILTRATION]: No network-related commands (e.g., curl, wget) or access to sensitive credentials (e.g., .env files, SSH keys) were found.
- [PROMPT_INJECTION]: The skill uses standard instructional language for navigation and does not attempt to override the agent's core instructions or safety guidelines.
- [DATA_EXPOSURE]: While the skill reads files from the codebase's
.agentlens/directory, these are limited to the tool's own documentation files and do not expose sensitive system or user data.
Audit Metadata