Trust Assessment
openclaw-defender received a trust score of 30/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 9 findings: 0 critical, 1 high, 8 medium, and 0 low severity. Key findings include Missing required field: name, Sensitive environment variable access: $HOME, Sensitive environment variable access: $GITHUB_URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 44/100, indicating areas for improvement.
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 Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unverified Blocklist Download (Supply Chain Risk & ReDoS) The `update-lists.sh` script downloads `blocklist.conf` from a remote URL (defaulting to `raw.githubusercontent.com`) without any integrity verification (e.g., hash check, GPG signature). This introduces a significant supply chain risk. If the remote repository or the download path is compromised, an attacker could inject a malicious `blocklist.conf`.
This is critical because `audit-skills.sh` uses the contents of `blocklist.conf` directly as regular expressions (joined by `|`) for `grep -qiE`. A malicious actor could inject a catastrophic regular expression (e.g., `(a+)+b`) into the blocklist. When `audit-skills.sh` processes this blocklist against a skill's `SKILL.md` containing matching patterns, it could lead to a Regular Expression Denial of Service (ReDoS) attack, causing the audit script to hang indefinitely and preventing further skill analysis. Implement cryptographic verification for downloaded blocklists. This could involve: 1. Downloading a signature file (e.g., GPG signature) alongside the blocklist and verifying it. 2. Downloading a hash file (e.g., SHA256) and comparing it against the downloaded blocklist's hash. 3. Pinning to a specific commit hash for the blocklist URL to prevent changes without explicit updates. Additionally, consider sanitizing or validating the regex patterns loaded from the blocklist in `audit-skills.sh` to mitigate ReDoS risks, even with a verified blocklist. | LLM | scripts/update-lists.sh:45 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/nightfullstar/openclaw-defender/SKILL.md:1 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/analyze-security.sh:5 | |
| MEDIUM | Sensitive environment variable access: $GITHUB_URL Access to sensitive environment variable '$GITHUB_URL' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/audit-skills.sh:148 | |
| MEDIUM | Sensitive environment variable access: $GITHUB_USER Access to sensitive environment variable '$GITHUB_USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/audit-skills.sh:152 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/check-integrity.sh:6 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/generate-baseline.sh:5 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/quarantine-skill.sh:12 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nightfullstar/openclaw-defender/scripts/runtime-monitor.sh:10 |
Scan History
Embed Code
[](https://skillshield.io/report/610cd479fc5e98f2)
Powered by SkillShield