security-audit

A workspace security check that looks for exposed credentials, unsafe file permissions, missing ignore rules, and hardcoded secrets.

In plain words
What is it for?
Use it to scan a project with a secret-scanning script or manual pattern checks, inspect the secrets directory and configuration file, and review related security settings.
Why use it?
It helps reveal sensitive information that may have been committed, readable by the wrong users, or left unprotected in project files.

Command

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 commands/saigonxiii/evc/security-audit
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01620
Opus 5 $0.00000 $0.00810
Sonnet 5 $0.00000 $0.00324
Haiku 4.5 $0.00000 $0.00162

Measured 3d ago against content hash 469f1400b135, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-audit scanned grade A with 1 finding 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Wrong permissions | `chmod 700 {{SECRETS_DIR}}` / `chmod 600 config.env` |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

_templates/commands/security-audit.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit

Full security scan of the workspace. Checks for credential leaks, file permissions, gitignore coverage, and hardcoded secrets.

Trigger

User invokes /security-audit or says "security check", "scan for secrets", "audit security"

Steps

1. Run secret scanner

if [ -f "{{PROJECT_ROOT}}/scripts/secret-scan.sh" ]; then
  bash "{{PROJECT_ROOT}}/scripts/secret-scan.sh"
else
  echo "SCANNER_MISSING"
fi

If the scanner script is missing, perform a manual scan:

# Search for common secret patterns in all non-binary files
grep -rn --include="*.md" --include="*.json" --include="*.env" --include="*.sh" --include="*.js" --include="*.ts" --include="*.yaml" --include="*.yml" \
  -E "(sk-[a-zA-Z0-9]{20,}|AKIA[A-Z0-9]{16}|ghp_[a-zA-Z0-9]{36}|xox[bpoas]-[a-zA-Z0-9-]+|-----BEGIN (RSA |EC )?PRIVATE KEY-----)" \
  "{{PROJECT_ROOT}}/" 2>/dev/null || echo "NO_SECRETS_FOUND"

2. Check file permissions

echo "=== Secrets Directory ==="
if [ -d "{{SECRETS_DIR}}" ]; then
  stat -f "%Lp %N" "{{SECRETS_DIR}}"
  # Should be 700
  ls -la "{{SECRETS_DIR}}/"
else
  echo "No secrets directory found"
fi

echo "=== Config File ==="
if [ -f "{{CONFIG_DIR}}/config.env" ]; then
  stat -f "%Lp %N" "{{CONFIG_DIR}}/config.env"
  # Should be 600
else
  echo "No config.env found"
fi

Expected permissions:

Path Expected Reason
{{SECRETS_DIR}}/ 700 Only owner can access secrets directory
{{CONFIG_DIR}}/config.env 600 Contains environment variables, may include keys
{{SECRETS_DIR}}/* 600 Individual secret files

3. Verify .gitignore coverage

echo "=== Gitignore Check ==="
MISSING=""

# Files that MUST be in .gitignore
REQUIRED_IGNORES=(
  "config.env"
  ".secrets/"
  "*.key"
  "*.pem"
  "node_modules/"
  ".env"
  ".env.*"
  "token.json"
)

for pattern in "${REQUIRED_IGNORES[@]}"; do
  if ! grep -q "$pattern" "{{PROJECT_ROOT}}/.gitignore" 2>/dev/null; then
    MISSING="$MISSING\n  MISSING: $pattern"
  fi
done

if [ -z "$MISSING" ]; then
  echo "All required patterns present"
else
  echo -e "GAPS FOUND:$MISSING"
fi

Read the full file on GitHub · 193 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 · 193 lines · 0 tokens per session scan A 469f1400b135

Subscribe to this mod's changes

security-audit is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,620 tokens. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.