Security Audit
seismic-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
seismic-automation received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Generic 'Workbench' Tool May Allow Arbitrary 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 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 | Generic 'Workbench' Tool May Allow Arbitrary Execution The skill documentation exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The generic nature of 'workbench' and the `run_composio_tool()` function suggests it could allow the execution of arbitrary Composio tools or commands. Without clear constraints or examples of its safe usage, this capability could be misused by a malicious prompt to instruct the LLM to perform command injection, data exfiltration, or other unauthorized actions by leveraging the broad permissions implied by a 'workbench' tool. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary execution, consider removing or restricting its exposure, or providing strict guidelines and examples for its safe use. Ensure `run_composio_tool()` is sandboxed and cannot access sensitive system resources or execute arbitrary commands outside the intended scope. | LLM | SKILL.md:65 |
Scan History
Embed Code
[](https://skillshield.io/report/021fefb81643ae1b)
Powered by SkillShield