Security Audit
updown-io-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
updown-io-automation received a trust score of 78/100, 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, 2 high, 0 medium, and 0 low severity. Key findings include Exposure of Authentication Link, Potential for Arbitrary Code 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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Exposure of Authentication Link The skill instructs the LLM to use `RUBE_MANAGE_CONNECTIONS` and notes that an 'auth link' will be returned if the connection is not active. Exposing such a link to the LLM creates a data exfiltration risk. A malicious prompt could instruct the LLM to extract and transmit this sensitive auth link, potentially allowing an attacker to complete the authentication process and gain unauthorized access to the user's Updown IO account. Implement mechanisms to prevent the LLM from directly outputting or transmitting sensitive URLs/tokens. For example, the authentication flow could be handled in a sandboxed browser environment or require explicit user confirmation outside the LLM's direct control. | LLM | SKILL.md:21 | |
| HIGH | Potential for Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH The skill mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies an environment for more general or programmatic execution, potentially allowing for arbitrary code or complex operations beyond simple API calls. If `run_composio_tool()` can execute arbitrary code, shell commands, or provides access to a broad range of system functionalities, it represents a significant security risk. An LLM, if prompted maliciously, could leverage this tool to execute unintended commands or access resources beyond the skill's intended scope. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, restrict its use or implement strict sandboxing and input validation. Ensure that the LLM's access to this tool is carefully controlled and monitored. | LLM | SKILL.md:58 |
Scan History
Embed Code
[](https://skillshield.io/report/f7cd08cefcffcac9)
Powered by SkillShield