wilma
Warn
Audited by Socket on Oct 23, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is largely coherent with its purpose: it accesses Wilma data and uses a public npm package from a consistent project/repo/site. Main risk comes from forwarding Wilma credentials and optional TOTP secrets into a third-party CLI and from the mutable `npx` fallback, plus handling sensitive student records and external attachment URLs. No clear credential harvesting, covert exfiltration, pre-execution abuse, or purpose mismatch is evident, so this is not malicious, but it carries meaningful trust and privacy risk.
Confidence: 88%Severity: 58%
Audit Metadata