Security Audit
rev-ai-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
rev-ai-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 tool execution capabilities 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 tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. `RUBE_MULTI_EXECUTE_TOOL` allows the LLM to execute any operation exposed by the `rev_ai` toolkit, given schema-compliant arguments. `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` further suggests the ability to execute arbitrary Composio tools within a remote environment. This grants the LLM broad and powerful access to Rev AI operations and potentially other connected systems. If the LLM is compromised (e.g., via prompt injection), these capabilities could be leveraged for unauthorized actions, data manipulation, or exfiltration within the connected services. Implement robust input validation and sanitization for all arguments passed to `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Ensure the LLM's execution environment is sandboxed and that the scope of tools accessible via `run_composio_tool()` is strictly limited to only necessary functions. Consider implementing human-in-the-loop approval for sensitive operations or operations that modify data. | LLM | SKILL.md:55 |
Scan History
Embed Code
[](https://skillshield.io/report/2f2c2f0922d5c754)
Powered by SkillShield