Claude Code, Skill
Agent Skills
Agent Skills, a skill listed in the PlugVet directory.
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.
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/claude-mythos/agent-instinct-system/SKILL.md, line 104
/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
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
skills/software-dev/git-worktrees/SKILL.md, line 81
subprocess.run(
skills/software-dev/git-worktrees/SKILL.md, line 89
subprocess.run(
skills/software-dev/git-worktrees/SKILL.md, line 95
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 collector. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
skills/infrastructure/cloudflare-workers/SKILL.md, line 54
async fetch(request: Request, env: Env): Promise<Response> {
skills/infrastructure/cloudflare-workers/SKILL.md, line 60
return agent.fetch(request);
skills/infrastructure/cloudflare-workers/SKILL.md, line 73
async fetch(request: Request): Promise<Response> {
Show more
skills/infrastructure/edge-rendering/SKILL.md, line 51
async fetch(request: Request, env: Env, ctx: ExecutionContext): Promise<Response> {
skills/infrastructure/observability/SKILL.md, line 107
await env.LOG_COLLECTOR.fetch("https://collector/ingest", {
skills/infrastructure/observability/SKILL.md, line 116
async fetch(request: Request, env: Env, ctx: ExecutionContext): Promise<Response> {
skills/software-dev/writing-plans/SKILL.md, line 85
**Verify**: `curl localhost:8787/users/test-id/preferences` returns 200
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
skills/claude-mythos/agent-instinct-system/SKILL.md, line 100
/\.env($|\.)/,
skills/claude-mythos/agent-instinct-system/SKILL.md, line 104
/id_rsa/,
skills/security/secret-protection/SKILL.md, line 65
name: Check .env files not committed
Show more
skills/security/secret-protection/SKILL.md, line 66
entry: bash -c 'git diff --cached --name-only | grep -E "\.env($|\.)" && exit 1 || exit 0'
.gitignore, line 3
*.log
.gitignore, line 4
.env
.gitignore, line 5
.env.local
skills/infrastructure/configuration-management/SKILL.md, line 15
Static configuration files (`.env`, `config.yaml`) force a deployment for every parameter change. In production systems handling real traffic, this creates unnecessary risk and del
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 7a04ccbde5f9. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. can reach collector. The description does not name that host. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 7a04ccbde5f96d4bfe99a15a7e6fd96a7a0d4cd6
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.