Claude Code, Skill
Cloud Platform Skills
43 production-grade, evaluated engineering skills for Cloud, Platform, SRE, Security and FinOps work — portable across every major AI coding agent, and usable by humans as runbooks, ADRs and SOPs.
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 f4e7fa65e209.
SECRETS_PATH_CREDENTIAL
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
scripts/compliance-check.py, line 135
r"(~/\.aws/credentials|~/\.ssh/id_[a-z0-9]+|~/\.kube/config|\.git-credentials|~/\.netrc|\.env\b)"
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
.agents/skills/ai-agent-security-llm-threats/SKILL.md, line 117
subprocess.run(["kubectl", "scale", f"deploy/{model_output}", "--replicas=3"], check=True)
scripts/generate-docs.py, line 202
shutil.rmtree(DOCS)
scripts/next-version.py, line 54
return subprocess.run( # noqa: S603
Show more
scripts/sync-all.py, line 156
shutil.rmtree(dst)
scripts/sync-all.py, line 183
shutil.rmtree(dest)
scripts/sync-all.py, line 297
shutil.rmtree(rules)
skills/devsecops-and-secops/ai-agent-security-llm-threats/SKILL.md, line 117
subprocess.run(["kubectl", "scale", f"deploy/{model_output}", "--replicas=3"], check=True)
.claude/skills/ai-agent-security-llm-threats/SKILL.md, line 117
subprocess.run(["kubectl", "scale", f"deploy/{model_output}", "--replicas=3"], check=True)
.cursor/rules/skills/ai-agent-security-llm-threats.mdc, line 115
subprocess.run(["kubectl", "scale", f"deploy/{model_output}", "--replicas=3"], check=True)
docs/devsecops-and-secops/ai-agent-security-llm-threats.md, line 117
subprocess.run(["kubectl", "scale", f"deploy/{model_output}", "--replicas=3"], check=True)
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach example.internal. The description does not name that host.
NETWORK_UNNAMED_HOST
.agents/skills/linux-sysadmin-troubleshooting/SKILL.md, line 94
curl -Iv https://example.internal
.agents/skills/performance-load-testing/SKILL.md, line 51
const res = http.get('https://api.staging.internal/v1/catalog', params);
skills/devops-core/junior-foundation/linux-sysadmin-troubleshooting/SKILL.md, line 94
curl -Iv https://example.internal
Show more
skills/devops-core/performance-load-testing/SKILL.md, line 51
const res = http.get('https://api.staging.internal/v1/catalog', params);
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL
scripts/compliance-check.py, line 135
r"(~/\.aws/credentials|~/\.ssh/id_[a-z0-9]+|~/\.kube/config|\.git-credentials|~/\.netrc|\.env\b)"
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 f4e7fa65e209. can delete files. can reach example.internal. The description does not name that host. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: f4e7fa65e2095a98d0352edee141ff83ffc5d7cd
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.