Security Audit
habitica-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
habitica-automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Broad tool execution via RUBE_REMOTE_WORKBENCH.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad tool execution via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. This function name suggests the ability to execute arbitrary Composio tools. If the underlying Rube MCP environment does not enforce strict access controls or sandboxing for tools executed via `run_composio_tool()`, this could lead to an LLM gaining excessive permissions to interact with various systems beyond the intended scope of Habitica. Ensure that the `RUBE_REMOTE_WORKBENCH` tool, specifically its `run_composio_tool()` capability, is strictly sandboxed and has fine-grained access controls. Limit the set of tools that can be executed via this function to only those necessary for the skill's intended purpose, or ensure that any executed tools operate within a least-privilege context. The skill documentation should clarify these limitations if they exist. | LLM | SKILL.md:69 |
Scan History
Embed Code
[](https://skillshield.io/report/06e3fcdee60ef913)
Powered by SkillShield