Security Audit
humanitix-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
humanitix-automation received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned Rube MCP dependency, Promotion of highly privileged `RUBE_REMOTE_WORKBENCH` tool.
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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned Rube MCP dependency The skill manifest specifies a dependency on 'rube' without a version constraint. This means the skill will always use the latest version of the Rube MCP, which could introduce vulnerabilities if a malicious or incompatible update is pushed to the Rube MCP. This constitutes a supply chain risk. Pin the Rube MCP dependency to a specific, known-good version or version range (e.g., `"rube": ["~1.0.0"]`) in the skill's manifest to mitigate supply chain risks. | LLM | SKILL.md:1 | |
| MEDIUM | Promotion of highly privileged `RUBE_REMOTE_WORKBENCH` tool The skill documentation promotes the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. This tool implies a general-purpose execution environment that could allow for arbitrary code execution or highly privileged operations if the agent is compromised or misdirected. The skill does not provide explicit warnings or guidance on restricting its use, increasing the risk of excessive permissions being exploited. Add explicit warnings about the power and potential risks of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Recommend strict sandboxing for agents using this tool and clear guidelines for its appropriate use to prevent misuse or command injection. If possible, restrict the scope of `run_composio_tool()` to only specific, pre-approved functions. | LLM | SKILL.md:65 |
Scan History
Embed Code
[](https://skillshield.io/report/f04f4afe49085b3f)
Powered by SkillShield