Trust Assessment
ado-multi-project-mapper received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Excessive permissions declared: Bash, Write, Edit, Glob.
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 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 | |
|---|---|---|---|---|
| CRITICAL | Excessive permissions declared: Bash, Write, Edit, Glob The skill explicitly declares highly privileged permissions including 'Bash', 'Write', 'Edit', and 'Glob'. The 'Bash' permission allows arbitrary command execution, which can lead to command injection, data exfiltration, and full system compromise if an attacker can control the input to shell commands. 'Write' and 'Edit' permissions allow modification of files, and 'Glob' allows listing files, significantly increasing the attack surface. These permissions are excessive for most skill functionalities and pose a severe security risk, especially when combined with an empty skill body that could be dynamically populated by untrusted input. Review and restrict the 'allowed-tools' to the absolute minimum required for the skill's functionality. Avoid 'Bash' permission unless strictly necessary and implement robust input validation and sandboxing if it must be used. Consider using more granular permissions or specific tool calls instead of broad file system access. If 'Bash' is truly required, ensure all shell commands are hardcoded or use extremely strict allow-listing for arguments, never passing untrusted input directly to the shell. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/189ebe0d28a5bf11)
Powered by SkillShield