Claude Code, Skill
Claude Api
Claude Api, a skill listed in the PlugVet directory.
Compatibility: Claude Code.
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 dbd4588f9e10, unchanged since the check below.
SECRETS_PATH_CREDENTIAL
Why this grade
- SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
shared/evals/report/build-report-lite.mjs, line 28
// `summary.json -> ~/.ssh/id_rsa`; the user later runs this builder (outside
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
shared/token-counting.md, line 51
before = subprocess.check_output(["git", "show", "HEAD:CLAUDE.md"], text=True)
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach api.anthropic.com. The description does not name that host. can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
curl/examples.md, line 16
curl https://api.anthropic.com/v1/messages \
curl/examples.md, line 37
response=$(curl -s https://api.anthropic.com/v1/messages \
curl/examples.md, line 63
curl https://api.anthropic.com/v1/messages \
Show more
curl/examples.md, line 102
curl https://api.anthropic.com/v1/messages \
curl/examples.md, line 127
curl https://api.anthropic.com/v1/messages \
curl/examples.md, line 165
curl https://api.anthropic.com/v1/messages \
curl/examples.md, line 192
curl https://api.anthropic.com/v1/messages \
curl/examples.md, line 217
response=$(curl -s https://api.anthropic.com/v1/messages \
shared/anthropic-cli.md, line 24
curl -fsSL "https://github.com/anthropics/ant
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
shared/anthropic-cli.md, line 65
# .env format - sets ANTHROPIC_AUTH_TOKEN (and ANTHROPIC_BASE_URL if the profile has one).
shared/managed-agents-environments.md, line 179
authorization_token: process.env.GITHUB_TOKEN, // repo clone token (!= MCP auth)
shared/evals/report/build-report-lite.mjs, line 28
// `summary.json -> ~/.ssh/id_rsa`; the user later runs this builder (outside
Show more
shared/managed-agents-self-hosted-sandboxes.md, line 70
const environmentKey = process.env.ANTHROPIC_ENVIRONMENT_KEY!;
shared/managed-agents-tools.md, line 90
{ "type": "user.tool_confirmation", "tool_use_id": "sevt_def456", "result": "deny", "deny_message": "Read .env.example instead" }
shared/evals/report/runner-scaffold.mjs, line 112
// ~/.ssh/id_rsa` planted after the startup preflight must not be read into
shared/preserved-thinking-migration/drop_block_probe.py, line 410
key = os.environ.get("ANTHROPIC_API_KEY")
shared/preserved-thinking-migration/drop_block_probe.py, line 411
token = os.environ.get("ANTHROPIC_AUTH_TOKEN")
typescript/managed-agents/README.md, line 127
authorization_token: process.env.GITHUB_TOKEN,
shared/managed-agents-onboarding-from-url.md, line 248
- **Never ask for a secret in the chat, and never write one to a file.** No `.env`, whatever the page does.
shared/preserved-thinking-migration/prefix_diff.py, line 1392
r"(os\.environ|process\.env|getenv\(|uuid|Math\.random\(|random\.choice|request_id|session_id|user_id|cwd\(\)|getcwd\(\)|hostname)",
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Note
a file was over the read cap and was not fully read.
OBFUSCATION_FILE_OVER_READ_CAP
shared/model-migration.md, line 1
# Model Migration Guide
Licence
Pass
A licence file is present (skills/claude-api/LICENSE.txt).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit dbd4588f9e10. requests shell access. The manifest names this permission. can reach api.anthropic.com. The description does not name that host. can reach a host that is not written as a fixed address. reads a credential or environment file. a file was over the read cap and was not fully read.
Date and source
Date checked:
github.com
Commit graded: dbd4588f9e1033efb41dad4bef2f7947c8993d44
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.