claude-code-dispatch
Warn
Audited by Socket on Sep 21, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated purpose matches code-task delegation, and the CLI appears to be an official Anthropic tool, so this is not strong malware evidence. However, the built-in use of `--dangerously-skip-permissions` makes the skill high risk because it suppresses approval gates while granting an external agent broad authority over the local codebase.
Confidence: 91%Severity: 83%
Audit Metadata