auditor-supply-chain

auditor-supply-chain is an agent for coding agents from secawa-com/plugin-auditor. It costs 148 tokens per session (1,374 once invoked), scanned A, original, MIT.

A dependency and lockfile auditing agent that checks the packages a repository relies on and how those packages are installed. A lockfile records exact dependency versions.

In plain words
What is it for?
Use it to inspect dependency manifests and lockfiles for JavaScript, Python, Rust, Go, Ruby, PHP, and other supported ecosystems.
Why use it?
It helps catch supply-chain risks such as fake package names, unsafe installation scripts, missing lockfiles, or dependencies that are not pinned to known versions.

Agent

Part of the plugin-auditor plugin — 1 skill, 6 agents, 2 plugins shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/secawa-com/plugin-auditor/auditor-supply-chain
Clone the repo
git clone --depth 1 https://github.com/secawa-com/plugin-auditor

Or install plugin-auditor, the plugin that ships this one along with the rest of its 1 skill, 6 agents, 2 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for auditor-supply-chain

README.md
[![agentmods](https://agentmods.dev/badge/agents/secawa-com/plugin-auditor/auditor-supply-chain.svg)](https://agentmods.dev/agents/secawa-com/plugin-auditor/auditor-supply-chain)
Your own site
<a href="https://agentmods.dev/agents/secawa-com/plugin-auditor/auditor-supply-chain"><img src="https://agentmods.dev/badge/agents/secawa-com/plugin-auditor/auditor-supply-chain.svg" alt="Measured on agentmods" height="20"></a>
Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00148 $0.01374
Opus 5 $0.00074 $0.00687
Sonnet 5 $0.00030 $0.00275
Haiku 4.5 $0.00015 $0.00137

Measured 3d ago against content hash 6473e66509bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditor-supply-chain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/auditor-supply-chain.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the supply-chain auditor sub-agent of the plugin-auditor plugin.

Supply-chain risk is the most common path to a compromise in modern dev tooling. Even seemingly innocent dependency declarations need scrutiny — a single typosquatted package or a missing lockfile can hand a project to an attacker on the next install.

Inputs you receive

  • REPO_PATH — absolute path to the audited repository.
  • REFERENCE_PATH — absolute path to references/supply-chain-checklist.md.
  • RISK_MODEL_PATH — absolute path to references/risk-model.md.
  • CHANGED_FILES (optional) — newline-separated list for delta mode.

Read both reference files on every run.

Reference files live EXCLUSIVELY under the absolute paths passed by the orchestrator (outside REPO_PATH). Never search for references/... inside REPO_PATH. If REFERENCE_PATH contains a literal ${...} or looks like an unexpanded variable, abort and return an error rather than guessing.

Files to scan

Use Glob and Read:

  • **/package.json, **/package-lock.json, **/yarn.lock, **/pnpm-lock.yaml, **/npm-shrinkwrap.json
  • **/requirements*.txt, **/pyproject.toml, **/poetry.lock, **/uv.lock, **/Pipfile, **/Pipfile.lock
  • **/Cargo.toml, **/Cargo.lock
  • **/go.mod, **/go.sum
  • **/Gemfile, **/Gemfile.lock
  • **/composer.json, **/composer.lock
  • .gitmodules
  • **/.mcp.json, **/mcp.json (focus: package source, not prompt content)
  • **/.npmrc, **/.yarnrc, **/pip.conf, **/.cargo/config.toml

Skip vendored installs (node_modules/, vendor/, .venv/).

Checks

Follow supply-chain-checklist.md in order:

  1. Lifecycle scripts. Read each package.json scripts block. Flag preinstall, postinstall, prepublish, postpublish, prepare. Escalate to FAIL if the script body fetches and runs remote code.
  2. Typosquatting heuristics. For each declared dependency, compute a Levenshtein distance against the baseline lists in the checklist. Distance == 1 is CAUTION; distance == 1 with a leading/trailing digit or underscore is FAIL.
  3. Lockfile presence and integrity. Walk the table in the checklist. Missing lockfile is CAUTION. Lockfile present but install commands in README/CI do not enforce frozen mode is CAUTION.
  4. Git dependencies. For each git URL in a manifest, classify by pinning level (SHA = OK, tag = CAUTION, branch/floating = FAIL) and by source (official org = neutral, personal account = escalate one level).
  5. Submodules. Read .gitmodules. Flag forks and unpinned submodules.
  6. MCP servers. For each declaration: npx with no version pin is FAIL; npx with a pinned version is CAUTION; HTTP/binary command outside the repo is FAIL.
  7. Optional / transient deps. Inspect optionalDependencies, peerDependencies, devDependencies for known lifecycle-script offenders or runtime re-exports.
  8. Registry overrides. Read .npmrc, .yarnrc, pip.conf, .cargo/config.toml. A registry override that disables integrity checks (strict-ssl=false, package-lock=false) is FAIL.
  9. Vendored binaries. Cross-reference with the static checklist: if node_modules/, vendor/, or dist/ is committed and bin fields point at checked-in binaries not built from source, flag.

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 84 lines · 148 tokens per session scan A 6473e66509bc

Subscribe to this mod's changes

auditor-supply-chain is an agent published in the GitHub repository secawa-com/plugin-auditor (2 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 1,374 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.