MCP, MCP server
Openclaw Superpowers
56 ready-to-use skills that make your AI agent autonomous, self-healing, and self-improving.
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.
Rescanned at commit a95a59d221d4, unchanged since the check below.
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.
skills/openclaw-native/community-skill-radar/radar.py, line 118
with urllib.request.urlopen(req, timeout=15) as resp:
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
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
skills/openclaw-native/mcp-health-checker/check.py, line 145
proc = subprocess.Popen(
skills/openclaw-native/skill-compatibility-checker/check.py, line 99
result = subprocess.run(
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
skills/openclaw-native/community-skill-radar/radar.py, line 118
with urllib.request.urlopen(req, timeout=15) as resp:
skills/openclaw-native/community-skill-radar/radar.py, line 157
with urllib.request.urlopen(req, timeout=15) as resp:
skills/openclaw-native/mcp-health-checker/check.py, line 244
with urllib.request.urlopen(req, timeout=timeout) as resp:
Show more
skills/core/skill-vetting/SKILL.md, line 24
- [ ] **Unknown network calls** - does it POST to a non-obvious domain? (`curl`, `fetch`, `requests.post`)
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_DOTENV
skills/openclaw-native/config-encryption-auditor/audit.py, line 38
SCAN_EXTENSIONS = {".yaml", ".yml", ".json", ".toml", ".env", ".conf", ".cfg", ".ini"}
skills/openclaw-native/config-encryption-auditor/audit.py, line 256
print(f"\nAdd these to your shell profile (~/.zshrc, ~/.bashrc) or a .env file.")
skills/openclaw-native/large-file-interceptor/intercept.py, line 50
".env", ".gitignore", ".dockerfile",
Show more
skills/openclaw-native/openclaw-config-advisor/advise.py, line 19
CONFIG_EXTS = {".json", ".yaml", ".yml", ".toml", ".env", ".conf"}
skills/core/project-onboarding/SKILL.md, line 34
- "Never commit secrets - use `.env.example`"
skills/core/skill-vetting/SKILL.md, line 25
- [ ] **Credential harvesting** - does it read `~/.ssh`, `~/.env`, API key env vars, or keychain?
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 a95a59d221d4. requests shell access. The manifest names this permission. 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: a95a59d221d44b89d4fc27a52934e24fb2060ddb
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.