Claude Code, Skill
Agent Tools
Reusable Agent Skills from agent-tools
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 edc8a215335a, unchanged since the check below.
PERMISSION_SHELL_UNDECLARED INSTALL_LIFECYCLE_HOOK SECRETS_PATH_CREDENTIAL
Why this grade
- PERMISSION_SHELL_UNDECLARED Medium
Runs shell commands that the manifest or description does not mention.
capabilities/log/hook.mjs, line 121
await fs.unlink(lockPath); - INSTALL_LIFECYCLE_HOOK Medium
A package install hook (preinstall, install, postinstall or prepare) runs a script.
package.json, line 39
prepare - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
scripts/publish.mjs, line 4
// Credentials persist in ~/.agent-tools/publish.npmrc, leaving ~/.npmrc untouched.
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. requests shell access. No manifest field names shell or command execution.
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES
capabilities/log/hook.mjs, line 121
await fs.unlink(lockPath);
capabilities/log/hook.mjs, line 133
await fs.unlink(lockPath).catch(() => {});
capabilities/log/hook.mjs, line 319
await fs.rm(path.join(CACHE_ROOT, entry.name), { recursive: true, force: true });
Show more
capabilities/log/hook.mjs, line 997
await fs.unlink(temp).catch(() => {});
capabilities/vision/lib/image-source.mjs, line 146
fs.rmSync(tempDir, { recursive: true, force: true });
capabilities/vision/lib/image-source.mjs, line 154
fs.rmSync(tempDir, { recursive: true, force: true });
capabilities/vision/lib/image-source.mjs, line 166
fs.rmSync(tempDir, { recursive: true, force: true });
capabilities/vision/lib/rate-limit.mjs, line 88
fs.rmSync(lockDir, { recursive: true, force: true });
Install and update
Concern
runs a script at install time.
INSTALL_LIFECYCLE_HOOK
package.json, line 39
prepare
Network
Concern
can reach a host that is not written as a fixed address. can reach registry.npmjs.org. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
capabilities/usage/lib/http.mjs, line 137
const response = await fetch(url, {
capabilities/vision/lib/providers/shared.mjs, line 181
// The timer must stay armed through the body read: fetch() resolves on
skills/systems/at-zentao/scripts/zentao-cli.mjs, line 275
const response = await fetch(this.endpoint("api.php/v1/tokens"), {
Show more
skills/systems/at-zentao/scripts/zentao-cli.mjs, line 307
const response = await fetch(this.endpoint(relative), {
tools/claude-skill-sync/lib.mjs, line 19
const response = await fetch("https://registry.npmjs.org/@anthropic-ai/claude-code/latest");
tools/claude-skill-sync/official.mjs, line 15
const response = await fetch(url);
docs/en/custom-gateway-routes.md, line 35
const login = await fetch(`${context.baseUrl}/api/user/login`, {
docs/zh-CN/custom-gateway-routes.md, line 31
const login = await fetch(`${context.baseUrl}/api/user/login`, {
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
capabilities/statusline/claude-statusline.mjs, line 269
process.env.PROVIDER_USAGE_API_KEY ||
capabilities/statusline/claude-statusline.mjs, line 270
process.env.ANTHROPIC_AUTH_TOKEN ||
scripts/publish.mjs, line 4
// Credentials persist in ~/.agent-tools/publish.npmrc, leaving ~/.npmrc untouched.
Show more
capabilities/statusline/claude-statusline.mjs, line 271
process.env.ANTHROPIC_API_KEY
capabilities/usage/core.mjs, line 76
hasProviderUsageKey: Boolean(process.env.PROVIDER_USAGE_API_KEY),
capabilities/usage/core.mjs, line 77
hasSub2apiKey: Boolean(process.env.SUB2API_API_KEY),
capabilities/usage/core.mjs, line 79
hasAnthropicAuthToken: Boolean(process.env.ANTHROPIC_AUTH_TOKEN),
capabilities/usage/core.mjs, line 80
hasAnthropicApiKey: Boolean(process.env.ANTHROPIC_API_KEY),
capabilities/usage/core.mjs, line 81
hasEnvOpenaiKey: Boolean(process.env.OPENAI_API_KEY),
scripts/publish.mjs, line 17
"publish.npmrc"
.gitignore, line 9
.env
.gitignore, line 11
!.env.example
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 edc8a215335a. can delete files. requests shell access. No manifest field names shell or command execution. runs a script at install time. can reach a host that is not written as a fixed address. can reach registry.npmjs.org. The description does not name that host. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: edc8a215335a7163b796052cd61bdb1e40ccad37
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.