skills-search
Warn
Audited by ZeroLeaks on Apr 16, 2026
Risk Level: MEDIUM
Scan Summary
This skill looks mixed overall, with low confidence. The scanned SKILL.md is materially reviewable, with no hidden execution path or secret-like content detected in the markdown. The skill increases prompt injection risk by weakening trust boundaries around sensitive tool routing lacks explicit confirmation boundary. Behavior analysis was not run.
Section Analysis (3)
TransparencyPASS
96/100
The scanned SKILL.md is materially reviewable, with no hidden execution path or secret-like content detected in the markdown.
Prompt InjectionWARNING
70/100
The skill increases prompt injection risk by weakening trust boundaries around sensitive tool routing lacks explicit confirmation boundary.
Agent BehaviorSkipped
Behavior analysis was not run.
Findings (1)
HIGH
Sensitive tool routing lacks explicit confirmation boundary
Coverage DetailsClick to expand
Audit Metadata