Skip to main content

Synopsis

profclaw security <subcommand> [flags]

Description

security manages profClaw’s security enforcement layer. Three policy levels control how strictly tool execution is governed. In standard and strict modes, certain tool calls require explicit approval before they run. This command lets you view the current policy, change it, review the audit log, and approve or deny pending requests.

Subcommands

SubcommandDescription
statusShow current policy level and pending approval count
set-policy <level>Set the security policy to permissive, standard, or strict
auditView the security audit log
approve <id>Approve a pending tool execution request
deny <id>Deny a pending tool execution request

Security Policy Levels

LevelDescription
permissiveAll tools run without approval
standardModerate and dangerous tools require approval
strictAll non-safe tools require explicit approval

security status

--json
boolean
Output as JSON with policy level, pending approval count, and last audit time.

security set-policy <level>

level
string
required
One of permissive, standard, or strict.
--json
boolean
Output the updated status as JSON.

security audit

-l, --limit
string
default:"20"
Maximum number of entries to show.
--pending
boolean
Show only entries with pending result status (awaiting approval).
--json
boolean
Output as JSON array.

security approve <id> / security deny <id>

id
string
required
Audit entry ID to approve or deny.
--reason
string
Reason for denial (only for deny subcommand).
--json
boolean
Output result as JSON.

Examples

profclaw security status