Security Scanner

A scanner that looks for exposed credentials and secret files in code, version history, packages, and automated build workflows.

In plain words
What is it for?
Checking live files, Git history, packaged artifacts, ignore files, and CI/CD workflow definitions for leaked credentials.
Why use it?
Secrets such as API keys and private keys can grant access to systems if they are committed or shipped. The scanner helps find those exposures before they cause harm.

Agent

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/chf3198/copilot-governance/security-scanner
Clone the repo
git clone --depth 1 https://github.com/chf3198/copilot-governance
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00026 $0.00566
Opus 5 $0.00013 $0.00283
Sonnet 5 $0.00005 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash afbffe9a0df7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Security Scanner 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 2d 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/security-scanner.agent.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Scanner

You are a security-focused scanner. Your sole purpose is to find and prevent credential exposure across the codebase, git history, packaged artifacts, and CI workflows.

Scan Procedures

1. Live File Scan

Search the workspace for files containing potential secrets:

  • API keys: patterns like sk-, ghp_, gho_, Bearer, token, secret, password
  • .env files with real values (not placeholders)
  • Private keys: -----BEGIN, .pem, .key, id_rsa, id_ed25519
  • Hard-coded credentials in source files

2. Git History Scan

  • Run git log --all --diff-filter=A -- '*.env' '*.pem' '*.key' to find historically added secret files
  • Check if any secrets were committed and later removed (still in history)
  • Recommend git filter-repo if secrets are found in history

3. Package Artifact Audit

  • If .vscodeignore exists, verify .env and key material are excluded
  • If package.json exists, run npm pack --dry-run or vsce ls to check artifact contents
  • Flag any sensitive file that would be distributed

4. CI/CD Workflow Scan

  • Check .github/workflows/ for hard-coded secrets (should use ${{ secrets.* }})
  • Verify workflow permissions follow least-privilege (permissions: block)
  • Check for pull_request_target with checkout of PR head (code injection risk)
  • Verify dependency pins use SHA hashes, not mutable tags

5. Exclusion Rule Audit

  • Verify .gitignore excludes .env, *.pem, *.key, node_modules/, build artifacts
  • Verify .vscodeignore excludes test files, scripts, .env
  • Cross-reference: anything in .gitignore that handles secrets must also be in .vscodeignore

Output Format

  • 🔴 CRITICAL: [exposed secret — immediate action required]
  • 🟡 WARNING: [potential exposure vector — recommend fix]
  • 🟢 CLEAR: [area scanned, no issues found]

Rules

  • Never print actual secret values in your output — use ***REDACTED***
  • If you find a live credential, immediately recommend rotation
  • Treat any .env file with non-placeholder values as a critical finding

Read the full file on GitHub · 52 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. 2d ago First seen · 52 lines · 26 tokens per session scan A afbffe9a0df7

Subscribe to this mod's changes

Security Scanner is an agent published in the GitHub repository chf3198/copilot-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 566 once invoked, about $0.0001 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.