Trust Assessment
reflect-check 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 Skill requests broad 'Read' and 'Bash' permissions.
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 | Skill requests broad 'Read' and 'Bash' permissions The skill's manifest explicitly declares 'Read' and 'Bash' permissions. 'Read' allows access to potentially any file the agent can read, and 'Bash' allows arbitrary shell command execution. While the skill is a diagnostic tool, these permissions are very broad and present a significant security risk if the underlying script (`reflect-check.sh`) is compromised or contains vulnerabilities. An attacker could potentially read sensitive files or execute malicious commands. Review the necessity of 'Read' and 'Bash' permissions. If possible, narrow down the scope of 'Read' to specific directories or file types required by the diagnostic tool. Ensure the `reflect-check.sh` script is thoroughly audited for security vulnerabilities, especially command injection and data exfiltration, given the broad permissions it operates under. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/8b22a588d3ed272e)
Powered by SkillShield