jianying-draft-digital-human
Warn
Audited by Socket on Oct 26, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s purpose and capabilities are mostly coherent for a JianYing digital-human workflow, and its approval gates are unusually explicit. The main concern is execution trust: meaningful actions depend on external CLI/adapter components and remote providers whose provenance and verification are not established in the supplied content, while handling sensitive face/voice data and paid operations. No direct evidence of credential theft, covert exfiltration, or malicious payload execution appears in the skill text itself.
Confidence: 84%Severity: 58%
Audit Metadata