speak

Warn

Audited by Socket on Sep 19, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill’s purpose is coherent and mostly local, but it depends on a PATH-shadowed `say` executable whose provenance is not documented or verifiable. There is no direct evidence of exfiltration or credential theft in the skill text, yet the unverifiable binary trust issue alone makes the skill high risk under the required scoring rules.

Confidence: 88%Severity: 78%
Audit Metadata
Analyzed At
Sep 19, 2026, 03:41 PM
Package URL
pkg:socket/skills-sh/lionad-morotar%2Fsay%2Fspeak%2F@be73c9995dacd9e1b93ab5b409515a35e26c67c8b749d76b0a7cb3cb66335186