Security Audit
page-x-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
page-x-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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned dependency in manifest, Broad tool access via dynamic 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 | |
|---|---|---|---|---|
| MEDIUM | Unpinned dependency in manifest The skill manifest specifies a dependency on 'rube' MCP without a version constraint. This can lead to unpredictable behavior, compatibility issues, or security vulnerabilities if a future version of 'rube' introduces breaking changes or malicious code. Relying on unpinned dependencies makes the skill vulnerable to supply chain attacks or unexpected functionality changes. Pin the dependency to a specific version or version range (e.g., `{"mcp": ["rube==1.2.3"]}` or `{"mcp": ["rube>=1.0.0,<2.0.0"]}`) to ensure consistent and secure behavior. | LLM | SKILL.md | |
| MEDIUM | Broad tool access via dynamic execution The skill enables the LLM to dynamically discover and execute a wide range of 'Page X operations' via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This grants the LLM broad access to the underlying Page X platform, potentially allowing it to perform unintended or malicious actions if prompted to do so. The skill itself does not impose fine-grained restrictions on which Page X operations can be performed, relying entirely on the scope of the 'page_x' toolkit. Implement stricter access controls or allow-lists for specific Page X operations that the LLM can execute. Consider adding a human-in-the-loop approval for sensitive operations. If possible, define a more granular scope for the `page_x` toolkit within Rube MCP to limit the actions an LLM can take. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/4e5b15c784446356)
Powered by SkillShield