Moltline Agent Governance & MCP Auditor

Audit Skill File

audit_skill_file

Read-onlyIdempotent

Audit an agent skill or instruction file before you trust it. FREE.

Checks for governance smells: prompt-injection and guardrail-bypass phrasing, concealment instructions ('don't tell the user'), exfiltration language, and exposed credential material. Typical input {"content": "<SKILL.md, system prompt, or tool description text>"} returns {"verdict": "reject — do not install" | "no governance red flags on a pattern pass", "findings": [{"severity": 1-5, "issue": "..."}], "note": "..."}.

Use before trusting a skill or instruction file that came from outside your own repository. Not for arbitrary untrusted input at run time (injection_scan). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": ""}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`content`	Yes	Full text of the skill file, system prompt, or tool description to audit.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description amplifies this with detailed behavioral traits: no protocol error on malformed input, returns error object with remediation advice, retry-safe after correction. This adds context beyond what annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

All text is front-loaded with clear purpose, then usage, behavior, and error handling. Every sentence adds unique value. No filler or repetition. The structure is logical and easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, the description doesn't need to detail return values, but it still does succinctly. With only one parameter and full schema coverage, the description is complete for all agent decision-making needs—purpose, usage, behavior, error handling, and examples.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds extra value by providing a working example of the input JSON ({"content": "..."}) and explaining what the content represents ('Full text of the skill file, system prompt, or tool description'), which goes beyond the bare schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool audits agent skill or instruction files for governance issues like prompt-injection and guardrail-bypass. It specifies the verb 'audit', the resource 'skill or instruction file', and distinguishes it from siblings like injection_scan which is for runtime input.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use ('before trusting a skill or instruction file from outside your own repository') and when not to ('Not for arbitrary untrusted input at run time (injection_scan)'). Provides an alternative sibling tool name, showing clear usage boundaries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Moltline Agent Governance & MCP Auditor tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose targeting a different aspect of agent governance: domain readiness, config auditing, skill file auditing, injection scanning, inventory, blast radius scoring, policy generation, and persona loading. Each description explicitly states what the tool is not for, eliminating ambiguity.

Naming Consistency2/5

Naming is inconsistent: some tools start with a verb (audit_mcp_config, get_auditor_persona), others with a noun (agent_readiness_scan, injection_scan, inventory_report, scope_check), and governance_policy is a plain noun phrase with no verb. There is no predictable pattern across the set.

Tool Count5/5

8 tools is well-scoped for the domain of agent governance and auditing. Each tool serves a distinct and necessary function without redundancy, covering readiness, configuration, skill files, injection, inventory, permissions, policy, and persona.

Completeness4/5

The tool surface covers the major governance activities: audit, scan, inventory, policy generation, and blast radius. A minor gap is the lack of a tool to verify compliance against a generated policy, but the existing audit tools can be used for that purpose.

Resources

Need Help?