Claude Code, Skill
Agent Skills
Skills I use with coding agents for engineering, design, writing, and media.
Compatibility: Not stated.
Grade C
One Medium finding. Read the report before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
NETWORK_HOST_FROM_INPUT
Why this grade
- NETWORK_HOST_FROM_INPUT Medium
A file takes a URL or endpoint as input and has no fixed host list.
scripts/bootstrap.sh, line 26
if ! curl -fsSL --retry 3 "$url" | tar -xz -C "$tmp" 2>/dev/null; then
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/gemini-tts/scripts/generate_tts.py, line 370
subprocess.run(command, check=True, capture_output=True)
skills/gemini-tts/scripts/generate_tts.py, line 392
subprocess.run(command, check=False)
Install and update
Note
README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell.
INSTALL_DOCUMENTED_INSTALLER
README.md, line 30
curl -fsSL https://raw.githubusercontent.com/iurysza/agent-skills/main/scripts/bootstrap.sh | bash
scripts/bootstrap.sh, line 4
# curl -fsSL https://raw.githubusercontent.com/iurysza/agent-skills/main/scripts/bootstrap.sh | bash
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
scripts/bootstrap.sh, line 26
if ! curl -fsSL --retry 3 "$url" | tar -xz -C "$tmp" 2>/dev/null; then
skills/chatgpt-imagegen/scripts/generate_image.py, line 326
with urllib.request.urlopen(url, timeout=120) as response_file:
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
skills/audio-transcribe/scripts/transcribe.ts, line 84
process.env.GEMINI_API_KEY,
skills/audio-transcribe/scripts/transcribe.ts, line 85
process.env.GOOGLE_API_KEY,
skills/audio-transcribe/scripts/transcribe.ts, line 86
process.env.OPENCODE_GOOGLE_API_KEY,
Show more
skills/chatgpt-imagegen/scripts/generate_image.py, line 55
key = os.environ.get("OPENAI_API_KEY") or os.environ.get("OPENCODE_OPENAI_API_KEY")
.gitignore, line 1
.DS_Store
.gitignore, line 2
.env
.gitignore, line 4
!.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 4ebf92118b4f. requests shell access. The manifest names this permission. README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell. accepts a host from input, with no fixed list in this file. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 4ebf92118b4f5b78175ea4a93c3786acb6b371a0
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.