meta-prompter
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose is plausible, but the skill's core functionality depends on an unpinned external npm CLI executed via Bash, with model config and possible credentials delegated to a package whose official publisher/source relationship was not verified from the provided evidence. Data flow is broadly consistent with prompt optimization, but the missing `references/rules.md` prevents validation of endpoint integrity and credential handling.
Confidence: 82%Severity: 58%
Audit Metadata