Security Audit
workiom-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
workiom-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 access to Workiom operations via generic execution tools.
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 access to Workiom operations via generic execution tools The skill exposes `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which allow the LLM to execute any available Workiom operation discovered via `RUBE_SEARCH_TOOLS`. This grants the LLM broad, unconstrained access to the connected Workiom account's capabilities. An attacker compromising the LLM could leverage this to perform arbitrary actions within Workiom, limited only by the Workiom account's permissions. This represents a significant attack surface. Implement fine-grained access control within the Rube MCP or Workiom toolkit to restrict the specific Workiom tools or operations that can be executed by the LLM. Alternatively, provide a mechanism for human approval for sensitive operations. If not possible, clearly document the broad access and the need for careful LLM prompting and sandboxing. | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/0dbd404959f5924c)
Powered by SkillShield