Trust Assessment
release-manager received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill declares `Bash` execution permission, Skill declares broad file system access (`Read`, `Write`, `Edit`).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Skill declares `Bash` execution permission The skill's manifest and declared permissions explicitly allow the use of `Bash` commands. This grants the AI agent the ability to execute arbitrary shell commands on the host system. This is a highly privileged and dangerous permission that significantly increases the attack surface for command injection, data exfiltration, and system compromise, especially if the agent processes untrusted user input or makes logical errors. The presence of this capability alone represents a critical security risk. Remove or restrict the `Bash` permission. Only grant specific, narrowly scoped tools required for the skill's function. If shell execution is absolutely necessary, consider using a sandboxed environment or a more constrained execution mechanism that does not allow arbitrary command execution. | LLM | SKILL.md | |
| HIGH | Skill declares broad file system access (`Read`, `Write`, `Edit`) The skill's manifest and declared permissions explicitly allow `Read`, `Write`, and `Edit` access to the file system. While some file operations might be necessary for a release manager, granting such broad permissions increases the risk of data exfiltration, unauthorized modification, or accidental data loss if the agent is compromised or misbehaves. This broad access, especially when combined with `Bash` execution, amplifies potential damage. Review and narrow down file system permissions to the absolute minimum required for the skill's functionality. Use specific file paths or capabilities instead of broad `Read`/`Write`/`Edit` if possible. Implement strict access controls and validation for any file operations. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/7fb92c261bcc6210)
Powered by SkillShield