Security Audit
workiom-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
workiom-automation received a trust score of 86/100, 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 Rube MCP.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad access to Workiom operations via Rube MCP The skill provides a mechanism for the LLM to discover and execute any available Workiom operation exposed through the Rube MCP and Composio's Workiom toolkit. The documentation explicitly instructs the LLM to use `RUBE_SEARCH_TOOLS` to find tools and `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` to execute them. This grants the LLM broad, unconstrained access to the Workiom API, without specific whitelisting of safe operations. If the Workiom toolkit includes sensitive, destructive, or data-exfiltrating operations, a compromised or misdirected LLM could exploit this broad access to perform unauthorized actions or exfiltrate data. Implement fine-grained access control for Workiom operations. Instead of allowing execution of *any* discovered tool, explicitly whitelist only necessary and safe Workiom tools in the skill's manifest or through a more constrained tool interface. If broad access is intended, ensure robust guardrails are in place at the LLM or platform level to prevent misuse, and clearly document the potential impact of this broad access. | LLM | SKILL.md:38 |
Scan History
Embed Code
[](https://skillshield.io/report/5b2585fa47ed6444)
Powered by SkillShield