Security Audit
dictionary-api-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
dictionary-api-automation received a trust score of 83/100, 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 tool execution via RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH implies general-purpose execution.
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 | RUBE_REMOTE_WORKBENCH implies general-purpose execution The skill mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. The term 'workbench' and the generic `run_composio_tool()` function suggest a powerful, potentially unconstrained execution environment. If this tool allows arbitrary code execution or access to system resources beyond the intended `dictionary_api` scope, it represents a significant security risk, enabling data exfiltration, command injection, or other malicious activities. The skill does not provide any explicit sandboxing or scope limitations for this tool. Clarify and strictly limit the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to only perform operations relevant to the Dictionary API, or remove this tool if its broad capabilities are not strictly necessary and securely sandboxed. Provide explicit documentation on its security implications and how its scope is enforced. | LLM | SKILL.md:80 | |
| MEDIUM | Broad tool execution via RUBE_MULTI_EXECUTE_TOOL The skill instructs the agent to use `RUBE_MULTI_EXECUTE_TOOL` with a `tool_slug` derived from `RUBE_SEARCH_TOOLS`. While `RUBE_SEARCH_TOOLS` is scoped to 'Dictionary API operations', the `RUBE_MULTI_EXECUTE_TOOL` itself does not enforce this scope. An attacker could potentially craft a prompt to the LLM to provide a `tool_slug` for a different, more privileged toolkit or operation if the LLM is aware of such tools, leading to unintended actions beyond the Dictionary API scope. The skill relies on the LLM's adherence to the 'search first' instruction rather than technical enforcement. Implement stricter validation or allow-listing of `tool_slug` values within the `RUBE_MULTI_EXECUTE_TOOL` call or the Rube MCP itself, ensuring only slugs from the intended `dictionary_api` toolkit can be executed. Alternatively, the skill definition could explicitly constrain the `tool_slug` parameter to a predefined list of safe Dictionary API operations. | LLM | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/ac3975484ee78a73)
Powered by SkillShield