email-header-injection
Pass
Audited by ZeroLeaks on Apr 16, 2026
Risk Level: LOW
Scan Summary
This skill looks clean overall, with low confidence. The skill has 1 transparency concern that weaken pre-use reviewability, mainly around potential hardcoded credential. 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.
Section Analysis (3)
TransparencyWARNING
61/100
The skill has 1 transparency concern that weaken pre-use reviewability, mainly around potential hardcoded credential.
Prompt InjectionPASS
92/100
The scanned skill keeps data and instructions reasonably separate and does not strongly encourage the agent to treat external content as policy.
Agent BehaviorSkipped
Behavior analysis was not run.
Findings (1)
CRITICAL
Potential hardcoded credential
Coverage DetailsClick to expand
Audit Metadata