ClawHub
Back to skill

Security audit

Sovereign Security Auditor

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is a coherent security-audit guide; its references to secrets and risky code patterns are part of the stated audit purpose.

Use this skill when you intentionally want a security-focused review of a repository or pull request. Expect the agent to look at configuration and secret-related filenames inside the scope you provide and to report sensitive findings in chat; avoid pointing it at files you do not want included in the audit.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (12)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · EXAMPLES.md (reported line 348)May include surrounding context.

md
db:
    image: postgres:15
    env_file:
      - .env
    environment:
      POSTGRES_PASSWORD: ${DB_PASSWORD}
      POSTGRES_USER: ${DB_USER}

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · EXAMPLES.md (reported line 373)May include surrounding context.

md
db:
    image: postgres:15
    env_file:
      - .env
    environment:
      POSTGRES_PASSWORD: ${DB_PASSWORD}
      POSTGRES_USER: ${DB_USER}

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · EXAMPLES.md (reported line 374)May include surrounding context.

md
node_modules/
dist/
.env
.env.local
.env.production
.env.staging
*.pem

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · EXAMPLES.md (reported line 375)May include surrounding context.

md
dist/
.env
.env.local
.env.production
.env.staging
*.pem
*.key

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 248)May include surrounding context.

md
### Files to Flag Immediately

- `.env`, `.env.local`, `.env.production`, `.env.staging`
- `credentials.json`, `service-account.json`
- `*.pem`, `*.key`, `*.p12`, `*.pfx` (private keys)
- `id_rsa`, `id_ed25519` (SSH keys)
- `.npmrc` with `_authToken`

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 251)May include surrounding context.

md
- `credentials.json`, `service-account.json`
- `*.pem`, `*.key`, `*.p12`, `*.pfx` (private keys)
- `id_rsa`, `id_ed25519` (SSH keys)
- `.npmrc` with `_authToken`
- `.pypirc` with passwords
- `wp-config.php`, `database.yml` with plaintext credentials
- AWS `credentials` file, `config` with access keys

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 255)May include surrounding context.

md
- `.pypirc` with passwords
- `wp-config.php`, `database.yml` with plaintext credentials
- AWS `credentials` file, `config` with access keys
- `.docker/config.json` with auth tokens

### Regex Patterns for Secret Detection

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 314)May include surrounding context.

md
- [ ] `httpOnly`, `secure`, `sameSite` flags on cookies

### Python
- [ ] No `eval()`, `exec()`, `os.system()`, `subprocess.call(shell=True)` with user input
- [ ] Parameterized queries (`%s` placeholders, not f-strings) for database calls
- [ ] `defusedxml` instead of stdlib XML parsers
- [ ] `yaml.safe_load()` instead of `yaml.load()`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file describes invocation using generic phrases such as "Audit this...", "Review this...", and "Check this..." without clarifying how specific the request must be or when the skill should not activate. Those verbs are common in everyday developer conversations, so the trigger scope is ambiguous and may cause unintended invocation overlap with other review-oriented skills.

Content

No source excerpt is available for this finding.

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.

md
Detect dangerous default or debug configurations.

**Patterns to detect:**
- `DEBUG=True` or `NODE_ENV=development` in production configs
- Default admin credentials
- Stack traces or debug info in error responses
- Directory listing enabled in web server config

Unsafe Defaults

Medium
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 154)May include surrounding context.

md
**Framework-specific:**
- React: `dangerouslySetInnerHTML` with unsanitized data
- Angular: `bypassSecurityTrustHtml()` usage
- Vue: `v-html` with user-controlled data
- EJS/Handlebars: `<%- %>` or `{{{ }}}` (unescaped output)
- Jinja2: `| safe` filter on user data

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · EXAMPLES.md (reported line 293)May include surrounding context.

md
**Impact:**
- Full database access (read, modify, delete all data)
- Financial loss via Stripe key misuse (charges, refunds, customer data)
- Full AWS account takeover (launch instances, access S3, escalate privileges)
- JWT forgery allowing authentication bypass for any user

**References:**

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
EXAMPLES.md:235