Skip to content

Agent governance vs Agentic actions auditor

Agent governance is an open-source agent skill for ai models and llm tooling. Agentic actions auditor is an open-source agent skill for ai models and llm tooling.

  • Agent governance has more GitHub stars (41,254 vs 8,243).
  • Agent governance is best for restrict which tools a coding agent can call and require approval for risky ones.
  • Agentic actions auditor is best for review my github actions workflows for prompt injection risks from issue comments.
What it is
Agent governance is an open-source agent skill for ai models and llm tooling.
Agentic actions auditor is an open-source agent skill for ai models and llm tooling.
Best for
Restrict which tools a coding agent can call and require approval for risky ones
Review my GitHub Actions workflows for prompt injection risks from issue comments
Kind
Skill
Skill
Pricing
Open source
Open source
Platforms
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
Claude Code
GitHub stars
41.3K
8.2K
Last commit
Nov 2026
Nov 2026
License
MIT
CC-BY-SA-4.0
Open source
Good for
Restrict which tools a coding agent can call and require approval for risky ones; Block prompts or tool arguments that contain secrets, credentials or destructive SQL; Record every agent action and denial for compliance review
Review my GitHub Actions workflows for prompt injection risks from issue comments; Check whether my Claude Code Action setup lets outside users trigger the agent; Audit a public repository's CI pipeline for unsafe AI agent configurations

What Agent governance does

  • Tool access policies

    Declarative policy objects define allowed tools, blocked tools and tools that need human approval.

  • Policy composition

    Layers org-wide, team and agent policies so that deny rules take precedence over allow rules.

  • Threat intent screening

    Regex-based signals score prompts for exfiltration, privilege escalation, destructive commands and prompt injection.

  • Governed tool decorator

    Wraps tool functions with allowlist, rate limit and argument content checks before execution.

  • Decay-based trust scoring

    Tracks agent reliability over time, with scores that erode without ongoing successful activity.

  • Append-only audit trail

    Logs agent actions and denials and exports them as JSON Lines for log aggregation.

What Agentic actions auditor does

  • AI action detection

    Identifies steps that call supported AI coding agent actions across all workflow files.

  • Prompt injection tracing

    Follows data from attacker-controlled event fields through env blocks into agent prompts.

  • Sandbox configuration review

    Flags dangerous sandbox and tool permission settings such as full-access modes and wildcard shell tools.

  • User allowlist checks

    Detects wildcard user allowlists that let any account trigger an AI agent.

  • Composite action resolution

    Looks one level into local composite actions and reusable workflows for hidden AI steps.

  • Severity-ranked report

    Produces findings grouped by workflow with severity, evidence and remediation notes.

Agent governance vs Agentic actions auditor: questions

Is Agent governance or Agentic actions auditor cheaper?

Both are open source. Compare current plans on each official site.

What is the difference between Agent governance and Agentic actions auditor?

Agent governance is an open-source agent skill for ai models and llm tooling. Agentic actions auditor is an open-source agent skill for ai models and llm tooling. Agent governance has more GitHub stars (41,254 vs 8,243).

Keep comparing