deepline-feedback
Warn
Audited by Socket on Mar 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s behavior is mostly aligned with its stated purpose and includes explicit user consent, but it sends potentially sensitive session and environment data off-device and depends on a required external deepline CLI whose public provenance was not verifiable from the provided evidence. Because a required unverifiable CLI is in the execution path, overall security risk is high even without clear evidence of malicious intent.
Confidence: 84%Severity: 72%
Audit Metadata