Audit History
wechat-channels-viral-video-breakdown - 2 audits
Version comparison
Capability and finding changes across audited versions, newest first.
Nov 6, 2026, 05:01 AM
Of 55 alerts, 54 are false positives involving Markdown, readable Chinese text, service links, identifiers, or scoped credential checks. One confirmed risk involves automatically executing an unpinned npm package with access to the agent environment. No evidence found of embedded credentials, credential exfiltration, reconnaissance, encoded payloads, or prompt injection in the reviewed files.
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (29)
🌐 Network access (3)
🔑 Env variables (7)
Nov 2, 2026, 11:55 AM
Of 44 static findings, one confirms external execution risk: npx automatically runs an unpinned third-party package with access to the configured environment. The other findings reflect Markdown formatting, legitimate service links and credential setup, application identifiers, or readable Chinese text. No evidence found of prompt injection, credential exfiltration, or concealed payloads in the supplied files; the external package implementation was not provided.
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.