Trust Assessment
devops 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, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Skill declares highly privileged `Bash` and broad filesystem access 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 15, 2026 (commit 1823c3f6). 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 highly privileged `Bash` and broad filesystem access permissions The skill's manifest declares `Bash`, `Read`, `Write`, and `Edit` permissions. The `Bash` permission allows the AI agent to execute arbitrary shell commands, which can lead to command injection, data exfiltration, or system compromise. `Read`, `Write`, and `Edit` permissions grant broad access to the filesystem, enabling the agent to read sensitive files, modify system configurations, or introduce malicious code. While a 'DevOps expert' skill might require some of these capabilities, the combination of `Bash` with broad filesystem access is extremely powerful and poses a significant security risk if the agent is compromised or misused through prompt injection or other means. Review and restrict `allowed-tools` to the absolute minimum necessary for the skill's intended function. If `Bash` is essential, implement strict input validation and sandboxing for any commands executed by the agent. Consider using more granular, purpose-built tools instead of direct `Bash` access where possible. Limit filesystem access (Read/Write/Edit) to specific, non-sensitive directories if these permissions are truly required. | LLM | SKILL.md | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | plugins/specweave-infrastructure/skills/devops/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/b5ff7ccbc458b02e)
Powered by SkillShield