company-research
Audited by ZeroLeaks on Apr 15, 2026
The SKILL.md is clear, well-structured, and straightforward to review, with no hidden execution paths or embedded secrets detected. It stays clear of blurring instruction and data boundaries and does not push the agent to treat external content as trusted policy. Tested scenarios did not show material prompt-injection risk or skill-induced worsening of downstream behavior, though confidence is low because behavior analysis was not run, meaning there is limited evidence on how the skill actually affects downstream agent actions in practice.
The scanned SKILL.md is materially reviewable, with no hidden execution path or secret-like content detected in the markdown.
The scanned skill keeps data and instructions reasonably separate and does not strongly encourage the agent to treat external content as policy.
Behavior analysis was not run.