Skip to main content
Glama

Ravi CI Guard: GitHub Actions security audit

Audit GitHub Actions workflows

audit_workflows
Read-only

Security + reliability audit of GitHub Actions workflows: repo=owner/name (all workflows at the default branch, or ref=), url= (one workflow file) or yaml= (the file text). About 30 line-accurate checks: pwn requests (pull_request_target / workflow_run running PR code), script injection from PR titles, branch names and comments, artifact poisoning, leaked credentials, GITHUB_TOKEN permissions, secrets: inherit, unpinned or compromised actions, deprecated actions that now fail, retired runners, self-hosted runners on PRs, ArtiPACKED token leaks, curl|sh, set-output, invalid structure, timeouts. Returns score/grade, findings (rule, severity, file:line, evidence, why, fix), commit-SHA pins resolved live from GitHub and two git-apply patches (safe, hardening). Needs a CI Guard pass (0.50 USDC = 24 h, 3 USDC = 30 days + Team Kit, 8 USDC = 90 days + Team Kit, by plain USDC transfer on Base; see payment_options), or pay per call over HTTP x402 ($0.10) at /v1/gha/audit.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_workflows"
  }
}

Input Schema

NameRequiredDescriptionDefault
pinNoResolve commit SHAs for unpinned actions and include them in the patch (default true)
refNoOptional branch, tag or commit SHA for repo= (default: the default branch)
urlNoAlternative: https URL of one workflow file (github.com blob/raw, raw.githubusercontent.com, gist)
passNoOptional CI Guard pass token (rcg1...). Better: set it once as the MCP header Authorization: Bearer <token>.
repoNoPublic GitHub repository, owner/name or https://github.com/owner/name (e.g. actions/checkout). Audits up to 12 files in .github/workflows at the default branch (or ref).
yamlNoAlternative: the workflow file text itself (POST JSON {"yaml": "..."} recommended; up to 64 KB)
min_severityNoOnly list findings at or above this severity (counts and score always cover everything). Default info

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description goes far beyond them by enumerating the ~30 checks performed, disclosing that commit SHAs are resolved live from GitHub, describing the return payload (score/grade, findings with rule/severity/file:line/evidence/fix, two git-apply patches), and stating the payment requirement with concrete pass durations and prices.

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

Conciseness3/5

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

The purpose and input modes are front-loaded, which is good, but the payment sentence is bulky and drifts into pricing tiers that belong in payment_options, and the long comma-separated check list is dense. It is informative but not tight.

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

Completeness4/5

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

With no output schema, the description carries the burden of explaining return values and does so thoroughly (score/grade, findings structure, patches). For a complex paid, network-dependent tool it is nearly complete, though it does not state failure behavior when no valid pass is supplied beyond 'needs a CI Guard pass'.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already carries the parameter documentation and the baseline is 3. The description reinforces the repo/url/yaml exclusivity and the default-branch scope of repo=, but adds little syntax or format detail the schema lacks.

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 names a specific action and resource ('Security + reliability audit of GitHub Actions workflows') and immediately specifies the three mutually exclusive input modes (repo=, url=, yaml=). An agent knows exactly what the tool does and how its inputs relate, without opening the schema.

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

Usage Guidelines3/5

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

Input-mode selection is well explained (repo= for all workflows at the default branch or ref=, url= for a single file, yaml= for raw text), and the header-based pass hint is useful. But there is no guidance on when to use this tool versus siblings like pin_actions, peek_workflows, or audit_sample, and no explicit 'when-not' case.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources