Trust Assessment
code-reviewer received a trust score of 76/100, 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, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Arbitrary File Write via --output 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 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 | |
|---|---|---|---|---|
| HIGH | Arbitrary File Write via --output Argument The Python scripts (`scripts/code_quality_checker.py`, `scripts/pr_analyzer.py`, `scripts/review_report_generator.py`) accept an `--output` argument that allows writing the generated JSON report to an arbitrary file path on the filesystem. This grants the skill excessive write permissions. An attacker could exploit this to overwrite critical system files (e.g., `/etc/passwd`, `/etc/hosts`) or to exfiltrate data if the `results` dictionary were to contain sensitive information in a future implementation of the `analyze` method. While the current JSON output is benign, the capability to write to any path is a significant security risk. Restrict the `--output` argument to a specific, controlled directory (e.g., a temporary directory or a designated output folder). Sanitize the path to prevent directory traversal. Alternatively, if writing to arbitrary paths is intended, ensure the script runs with minimal necessary permissions and that the content written is always benign. This issue is present in all three Python scripts: `scripts/code_quality_checker.py`, `scripts/pr_analyzer.py`, and `scripts/review_report_generator.py`. | LLM | scripts/code_quality_checker.py:109 | |
| 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 | |
| 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/21266e7443728d9c)
Powered by SkillShield