Trust Assessment
disclawd received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unpinned external plugin installation.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned external plugin installation The skill recommends installing an OpenClaw plugin directly from a GitHub repository URL (`github.com/disclawd/openclaw-disclawd`) without specifying a version, commit hash, or tag. This makes the installation vulnerable to supply chain attacks, as the content of the plugin could change at any time, leading to arbitrary code execution on the host system. An attacker could compromise the repository or the skill author could inadvertently introduce malicious code. Pin the plugin installation to a specific version, commit hash, or tag (e.g., `github.com/disclawd/openclaw-disclawd@v1.0.0` or `github.com/disclawd/openclaw-disclawd@<commit_hash>`) to ensure deterministic and verifiable installations. Alternatively, host the plugin package in a trusted, versioned package registry. | LLM | SKILL.md:26 |
Scan History
Embed Code
[](https://skillshield.io/report/a30450aebc65ca68)
Powered by SkillShield