Claude Code, Skill
Skill Fetch
Search, discover, and install AI agent skills from 9 registries with quality scoring, security labels, and cross-platform support
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 5a56044989e6, 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/skill-fetch/references/interaction-patterns.md, line 99
| **D** | System Modification | High | Writes to `/etc/`, `~/.ssh/`, `~/.bashrc`, `~/.zshrc`, `~/.claude/CLAUDE.md`, `crontab`, modifying shell profiles or global config | - AGENT_IGNORE_INSTRUCTIONS Medium
Text tells the agent to ignore earlier instructions.
skills/skill-fetch/references/interaction-patterns.md, line 135
- `Ignore previous instructions`、`Ignore all prior instructions`
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
Pass
No shell or command call was found in the code. This check does not read permissions an entry declares. A permission line to run shell commands, write or edit files and fetch web content was found in this repository, and it may apply to this entry.
Install and update
Note
README documents an installer that pipes a download into a shell.
INSTALL_DOCUMENTED_INSTALLER
README.md, line 61
curl -fsSL https://raw.githubusercontent.com/girofu/skill-fetch/main/install.sh | bash
README.md, line 67
curl -fsSL https://raw.githubusercontent.com/girofu/skill-fetch/main/install.sh | bash -s -- --agent claude
Network
Concern
can reach a host that is not written as a fixed address. can reach prompts.chat. The description does not name that host. can reach api.github.com. The description does not name that host. can reach www.skillhub.club. The description does not name that host. can reach www.skillsdirectory.com. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
install.py, line 54
with urllib.request.urlopen(url, timeout=15) as resp:
install.sh, line 68
command -v curl >/dev/null 2>&1 || die "curl is required but not installed."
install.sh, line 86
if ! curl -fsSL --retry 2 --connect-timeout 10 -o "$dest" "$url"; then
Show more
skills/skill-fetch/references/platform-adapters.md, line 57
curl -s "https://skills.sh/api/search?q={query}&limit=5"
skills/skill-fetch/references/platform-adapters.md, line 58
curl -s "https://prompts.chat/skills?q={query}"
skills/skill-fetch/references/platform-adapters.md, line 64
curl -s "https://api.github.com/search/repositories?q={query}+claude+skill&sort=stars&per_page=5"
skills/skill-fetch/references/platform-adapters.md, line 91
└── GitHub raw download (all - curl or WebFetch)
skills/skill-fetch/references/search-sources.md, line 72
curl -s "https://skills.sh/api/search?q={query}&limit=5"
skills/skill-fetch/scripts/fetch-skillhub.sh, line 18
RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "https://www.skillhub.club/api/v1/skills/search" \
skills/skill-fetch/scripts/fetch-skills-directory.sh, line 28
RESPONSE=$(curl -s -w "\n%{http_code}" "https://www.skillsdirectory.com/api/v1/skills?q=${ENCODED_QUERY}&limit=5&securityGrade=A" \
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL
skills/skill-fetch/references/interaction-patterns.md, line 98
| **C** | Data Exfiltration | High | `curl -X POST` / `fetch(... method: 'POST')` combined with local file reads or env var access; sending `$HOME`, `$SSH_KEY`, `$API_KEY`, `.env`
skills/skill-fetch/references/interaction-patterns.md, line 99
| **D** | System Modification | High | Writes to `/etc/`, `~/.ssh/`, `~/.bashrc`, `~/.zshrc`, `~/.claude/CLAUDE.md`, `crontab`, modifying shell profiles or global config |
Agent instructions
Serious
instructions tell the agent to ignore earlier instructions.
AGENT_IGNORE_INSTRUCTIONS
skills/skill-fetch/references/interaction-patterns.md, line 135
- `Ignore previous instructions`、`Ignore all prior instructions`
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 5a56044989e6. README documents an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. can reach prompts.chat. The description does not name that host. can reach api.github.com. The description does not name that host. can reach www.skillhub.club. The description does not name that host. can reach www.skillsdirectory.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: 5a56044989e637d0a54703ce496b6f99d8edae5b
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.