using-ably
Audited by ZeroLeaks on Apr 15, 2026
**Executive Summary** The skill raises transparency concerns: the scan flagged obfuscated or encoded execution paths and hidden or dense payload-like content, which meaningfully weaken a reviewer's ability to assess what the skill actually does before loading it. On prompt injection, the skill stays reasonably clear—it does not appear to blur instruction/data boundaries or push the agent to treat external content as trusted policy. However, behavior analysis was not run, so there is no direct evidence on whether loading this skill materially changes downstream agent behavior compared to a no-skill baseline. Confidence is low overall: the transparency issues make it harder to fully trust the skill's intent, and without behavioral testing, the verdict of WARNING reflects genuine uncertainty rather than a confirmed risk.
The skill has 2 transparency concerns that weaken pre-use reviewability, mainly around obfuscated or encoded execution path and hidden or dense payload-like content.
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.
Obfuscated or encoded execution path
Hidden or dense payload-like content