Security Sentinel#

Scans a skill directory for security issues, misconfigurations, and best practices.

What It Detects#

CategoryExamplesSeverityDangerous calls (critical)os.system, eval, exec🔴 CriticalDangerous calls (warning)subprocess.run, os.popen🟡 WarningHardcoded secretsAPI keys, tokens, passwords, credentials in string literals🔴 CriticalNetwork callsrequests.get, urllib.request.urlopen, http.client🟡 WarningObfuscationgetattr indirection, __import__/ importlib dynamic loading, chr()-encoded strings🔴 CriticalHidden filesFiles and directories starting with . (e.g. .env, .hidden_script.py)🟡 Warning

Severity Model#

The scanner uses a three-tier severity system:

StatusMeaning🔴 CRITICALImmediate security risk — hardcoded secrets, eval/ exec, os.system, obfuscation detected. Requires urgent review.🟡 WARNINGPotential risk — subprocess usage, network calls, hidden files. Review recommended.🟢 OKNo findings. File is clean.

Each file gets an individual severity rating. The overall status is the highest severity across all files — if even one file is red, the entire scan is marked CRITICAL.

Obfuscation Defenses (Defensive Depth)#

The scanner catches three common bypass techniques:

1. getattr indirection — getattr(os, 'system')('whoami') is flagged because the second argument resolves to a known dangerous attribute name.
2. Dynamic imports — __import__('subprocess') and importlib.import_module('subprocess') are both detected and flagged as dangerous module loads.
3. String construction — Secrets built via concatenation ( key = "sk-" + "abcd...") or chr() sequences are resolved at scan time and matched against secret patterns.

Usage#

The scan_skill tool accepts a path argument pointing to a skill directory. It runs scanner.py against all .py files in that directory tree and returns a Markdown report with tables of findings grouped by file and category.