Security Audit
apiverve-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
apiverve-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 execution capabilities via RUBE_REMOTE_WORKBENCH, Potential for credential exposure through RUBE_MANAGE_CONNECTIONS.
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 execution capabilities via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. This implies a powerful capability to execute arbitrary Composio tools or operations. Without strict input validation and sandboxing, a malicious prompt could trick the LLM into performing unauthorized actions, potentially leading to data manipulation, deletion, or exfiltration through the underlying Composio toolkit. The scope of `run_composio_tool()` is not defined, making it a high-risk component. Clarify and restrict the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that the LLM's use of this tool is heavily constrained, validated, and sandboxed to prevent arbitrary code execution or unauthorized operations. Provide explicit examples of safe usage and warnings against misuse. | LLM | SKILL.md:66 | |
| MEDIUM | Potential for credential exposure through RUBE_MANAGE_CONNECTIONS The skill describes using `RUBE_MANAGE_CONNECTIONS` to establish API connections, including following 'auth links' for setup. If a malicious user can manipulate the LLM to expose these auth links or sensitive connection details, it could lead to credential harvesting, session hijacking, or unauthorized access to the Apiverve account. The LLM must be extremely careful not to output or redirect sensitive authentication information. Instruct the LLM to never output or share authentication links or sensitive connection details directly to the user. Implement strict internal policies for handling and displaying such information, ensuring it is only used for its intended purpose (e.g., opening a browser tab for the user, not displaying the URL). | LLM | SKILL.md:27 |
Scan History
Embed Code
[](https://skillshield.io/report/8e2bfa7e57f60f45)
Powered by SkillShield