Trust Assessment
codex-review received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unpinned skill installation from GitHub.
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 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Unpinned skill installation from GitHub The installation command `npx skills add -g BenedictKing/codex-review` fetches the skill directly from a GitHub repository without specifying a version, commit hash, or tag. This means that any future updates to the `BenedictKing/codex-review` repository could introduce malicious code, which would be automatically installed by users without explicit review. This poses a supply chain risk as the integrity of the installed skill depends entirely on the ongoing security of the remote repository and its maintainers. Pin the skill installation to a specific version, commit hash, or tag (e.g., `npx skills add -g BenedictKing/codex-review@v1.0.0` or `npx skills add -g BenedictKing/codex-review#<commit_hash>`) to ensure reproducibility and prevent unexpected malicious updates. | Static | SKILL.md:15 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/e9bbac926e8a4f32)
Powered by SkillShield