Security Audit
humanloop-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
humanloop-automation received a trust score of 80/100, 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 Broad access to Humanloop operations via Rube MCP, Unpinned Rube MCP dependency in manifest.
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 | Broad access to Humanloop operations via Rube MCP The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` with a broad `use_case: "Humanloop operations"` (line 43) and `use_case: "your specific Humanloop task"` (line 53). This allows the LLM to discover and subsequently execute any available Humanloop tool via `RUBE_MULTI_EXECUTE_TOOL`. This grants the LLM excessive permissions to interact with the Humanloop platform, potentially leading to unauthorized data access, modification, or deletion if the LLM is compromised or misused. The `RUBE_REMOTE_WORKBENCH` also implies broad execution capabilities. Restrict the `use_case` parameter in `RUBE_SEARCH_TOOLS` to a minimal set of required Humanloop operations. Implement fine-grained access control within the Composio toolkit or Humanloop platform to limit the scope of actions an agent can perform. Consider using a whitelist of allowed tool slugs instead of broad discovery. | LLM | SKILL.md:43 | |
| MEDIUM | Unpinned Rube MCP dependency in manifest The skill manifest declares a dependency on `rube` within the `mcp` category without specifying a version (`"mcp": ["rube"]`). This 'unpinned' dependency means that any version of `rube` could be loaded, including potentially vulnerable or malicious future versions, introducing a supply chain risk. This lack of version pinning makes the skill susceptible to unexpected behavior or security vulnerabilities if the `rube` dependency changes. Pin the `rube` dependency to a specific, known-good version in the skill manifest (e.g., `"rube": ["rube@1.2.3"]`) to ensure deterministic and secure dependency resolution. | LLM | Manifest (frontmatter JSON) |
Scan History
Embed Code
[](https://skillshield.io/report/40882dddee46919c)
Powered by SkillShield