← Back to search

io.github.dingdawg/dingdawg-loop

dingdawg Scanned 14d ago

Safe scheduled AI agents with governance gates. Verified, receipted, fail-closed.

B
87.2 / 100

Versions

2.0.8latest
first seen Jun 5, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 6

register_loop
annotations: none low

Register a scheduled agent loop. Stores the loop definition with its cron schedule, action type, and risk tier. The loop is created in

name string schedule string action_type string description string
execute_loop
annotations: none low

Manually trigger a loop execution. ALWAYS runs the governance gate first — if governance denies or errors, the loop body does NOT execute. Returns the governance receipt and execution outcome. This is the core DDLP safety mechanism: declare intent, get governed, then act.

loop_id string execution_notes string
list_loops
annotations: none low

List all registered loops with their current status, schedule, risk tier, and last execution result. Use this to see what loops exist and their governance health.

pause_loop
annotations: none low

Pause a loop so it cannot be executed. Paused loops reject execute_loop calls until resumed. Use this to safely stop a loop without deleting its history.

reason string loop_id string
resume_loop
annotations: none low

Resume a paused loop so it can be executed again. Clears the pause reason from metadata.

loop_id string
loop_audit
annotations: none low

Get the execution history for a specific loop. Shows every governance decision, outcome, and timestamp. Use this to audit how a loop has been behaving over time.

limit number loop_id string

Permissions 3

network medium
Server uses network capabilities via: fetch()
filesystem low
Server uses filesystem capabilities via: fs sync ops
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 23

low
Tool 'register_loop' has no annotations annotation_checker · 100%
low
Tool 'execute_loop' has no annotations annotation_checker · 100%
low
Tool 'list_loops' has no annotations annotation_checker · 100%
low
Tool 'pause_loop' has no annotations annotation_checker · 100%
low
Tool 'resume_loop' has no annotations annotation_checker · 100%
low
Tool 'loop_audit' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.0.0 (GHSA-w48q-cv73-mx4w) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Tool: register_loop manifest_parser · 70%
info
Tool: execute_loop manifest_parser · 70%
info
Tool: list_loops manifest_parser · 70%
info
Tool: pause_loop manifest_parser · 70%
info
Tool: resume_loop manifest_parser · 70%
info
Tool: loop_audit manifest_parser · 70%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (1) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 70%
low
Permission: filesystem access detected permission_analyzer · 90%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 4 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%