Claude Code, Skill
SecuritySkills
Drop structured security skills into your AI coding agent.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High finding. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 70bc259bb01a, unchanged since the check below.
SECRETS_PATH_CREDENTIAL AGENT_IGNORE_INSTRUCTIONS
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skills/cloud/aws-review/SKILL.md, line 85
**/.aws/credentials - AGENT_IGNORE_INSTRUCTIONS Medium
Text tells the agent to ignore earlier instructions.
SECURITY.md, line 45
`ignore previous instructions and`, `ignore all previous instructions`, `you are now a`, `you are now in`, `disregard your`, `disregard all previous`
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.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
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
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
skills/appsec/secure-code-review/SKILL.md, line 89
cmd := exec.Command("sh", "-c", "cat "+filename)
skills/ai-security/llm-top-10/SKILL.md, line 207
- Search for model output variables flowing into `eval()`, `exec()`, `subprocess.run()`, `os.system()`, database query construction, or ORM raw query methods.
skills/appsec/owasp-top-10-web/SKILL.md, line 190
- OS command execution with user-controlled arguments (`exec`, `system`, `child_process.exec`, `os.system`, `subprocess.call` with `shell=True`).
Show more
skills/appsec/owasp-top-10-web/SKILL.md, line 233
- For OS commands, use array-based APIs (e.g., `subprocess.run([...])` without `shell=True`); validate and allowlist expected argument values.
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 169.254.169.254. The description does not name that host. can reach partner-api.example.com. The description does not name that host. can reach third-party-api.com. The description does not name that host. can reach enrichment-api.com. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
scripts/generate_quality_scorecard.rb, line 180
skills = index.fetch("skills", [])
scripts/validate_index.rb, line 172
role.fetch("skills", []).each do |skill_id|
scripts/validate_skill_schema.rb, line 111
schema.fetch("required", []).each do |field|
Show more
scripts/validate_skill_schema.rb, line 115
properties = schema.fetch("properties", {})
scripts/validate_skill_schema.rb, line 116
unless schema.fetch("additionalProperties", true)
skills/appsec/api-security/api-top10-checklist.md, line 388
response = requests.get(url) # Attacker sends http://169.254.169.254/latest/meta-data/
skills/appsec/api-security/api-top10-checklist.md, line 530
partner_data = requests.get("https://partner-api.example.com/products").json()
skills/appsec/api-security/api-top10-checklist.md, line 537
response = requests.get("https://third-party-api.com/data", verify=False)
skills/cloud/container-security/cis-benchmarks.md, line 81
CMD curl -f http://localhost:8080/health || exit 1
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
skills/cloud/aws-review/SKILL.md, line 85
**/.aws/credentials
skills/cloud/container-security/cis-benchmarks.md, line 125
COPY .env /app/.env
skills/cloud/container-security/cis-benchmarks.md, line 126
COPY credentials.json /app/
Show more
skills/cloud/container-security/cis-benchmarks.md, line 130
RUN --mount=type=secret,id=npmrc,target=/root/.npmrc npm install
skills/cloud/container-security/cis-benchmarks.md, line 146
COPY.*\.env
skills/cloud/container-security/cis-benchmarks.md, line 162
.env
skills/devsecops/secrets-management/SKILL.md, line 61
**/.env
skills/devsecops/secrets-management/SKILL.md, line 62
**/.env.*
Agent instructions
Serious
instructions tell the agent to ignore earlier instructions.
AGENT_IGNORE_INSTRUCTIONS
SECURITY.md, line 45
`ignore previous instructions and`, `ignore all previous instructions`, `you are now a`, `you are now in`, `disregard your`, `disregard all previous`
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 70bc259bb01a. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. can reach 169.254.169.254. The description does not name that host. can reach partner-api.example.com. The description does not name that host. can reach third-party-api.com. The description does not name that host. can reach enrichment-api.com. The description does not name that host. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.
Date and source
Date checked:
github.com
Commit graded: 70bc259bb01abb3015ad2ad859ad5253cbf0bcab
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.