ln-521-test-researcher
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to conduct research using web search tools and project documentation (Kanban board) to identify user pain points and technical edge cases. This behavior is consistent with its stated purpose and utilizes project-authorized tools.
- [SAFE]: The skill includes a set of local utility scripts (in
references/scripts/) that manage the agent's execution state, including phases, checkpoints, and run history. These scripts perform routine file operations within the project's.hex-skills/directory and do not execute external code or access sensitive system paths. - [SAFE]: Data handled by the skill consists of research findings and project task identifiers. There are no patterns suggesting unauthorized data exposure, exfiltration, or the handling of hardcoded credentials.
- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the skill instructions or supporting scripts.
Audit Metadata