Trust Assessment
openclaw-security received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Reliance on external skill repository (ClawHub), Potential command injection via --workspace argument.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Reliance on external skill repository (ClawHub) The skill explicitly states that it installs and updates other security skills from 'ClawHub'. This introduces a significant supply chain risk. If ClawHub is compromised, or if the skill installation/update mechanism lacks robust verification (e.g., cryptographic signatures, checksums), malicious skills could be introduced into the user's environment. Implement robust verification mechanisms (e.g., cryptographic signatures, checksums) for skills downloaded from ClawHub. Clearly document the security posture of ClawHub and the update process, including how skill integrity is ensured. | LLM | SKILL.md:10 | |
| MEDIUM | Potential command injection via --workspace argument The skill's commands accept a `--workspace` argument, which specifies a file path. If this argument is derived from untrusted user input and is not properly sanitized by the calling agent or the `security.py` script before being used in shell commands (e.g., `subprocess.run(..., shell=True)`), it could allow an attacker to inject arbitrary shell commands. Ensure that any user-provided input for the `--workspace` argument is strictly validated and sanitized to prevent shell metacharacters. The `security.py` script should use `subprocess.run` with `shell=False` and pass arguments as a list, or use `shlex.quote` if shell execution is unavoidable. The agent invoking this skill should also sanitize user-provided paths. | LLM | SKILL.md:8 |
Scan History
Embed Code
[](https://skillshield.io/report/078dd021c1ffb52c)
Powered by SkillShield