Security Audit
formcarry-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
formcarry-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 capability via RUBE_REMOTE_WORKBENCH, Unpinned Rube MCP dependency.
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 17, 2026 (commit 99e2a295). 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 tool execution capability via RUBE_REMOTE_WORKBENCH The skill exposes the `RUBE_REMOTE_WORKBENCH` tool which, when used with `run_composio_tool()`, implies the ability to execute arbitrary Composio tools, not just those specifically related to Formcarry. This grants the LLM a broad execution surface that could be exploited for actions beyond the intended scope of the Formcarry automation skill, potentially leading to unauthorized data access or manipulation through other connected toolkits if the underlying `run_composio_tool()` is not strictly sandboxed or scoped. Restrict the `RUBE_REMOTE_WORKBENCH` to only execute Formcarry-specific tools, or provide a more granular tool for bulk operations that explicitly limits its scope. Ensure `run_composio_tool()` is strictly sandboxed and cannot execute arbitrary code or access unintended resources outside the Formcarry context. | LLM | SKILL.md:68 | |
| MEDIUM | Unpinned Rube MCP dependency The skill's manifest declares a dependency on the `rube` MCP without specifying a version. This means that any future version of the `rube` MCP could be used, potentially introducing breaking changes, vulnerabilities, or malicious code without explicit review or consent. This is a common supply chain risk where updates to a dependency could inadvertently compromise the skill's security or functionality. Pin the `rube` MCP dependency to a specific, known-good version in the manifest to ensure consistent and secure behavior. Regularly review and update the pinned version to incorporate necessary security patches and features. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/d6d6cd6a72270f78)
Powered by SkillShield