Security Audit
icims-talent-cloud-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
icims-talent-cloud-automation received a trust score of 88/100, 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 Skill promotes use of broad-access tools for external system management and 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 | Skill promotes use of broad-access tools for external system management and execution The skill instructs the agent to use `RUBE_MANAGE_CONNECTIONS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`. These tools grant significant control over the Icims Talent Cloud system:
* `RUBE_MANAGE_CONNECTIONS` allows managing connections, including potentially handling authentication links. Misuse could lead to connection disruption or unauthorized access.
* `RUBE_MULTI_EXECUTE_TOOL` allows the execution of arbitrary discovered tools within the Icims Talent Cloud, enabling a wide range of operations.
* `RUBE_REMOTE_WORKBENCH` enables bulk operations and `run_composio_tool()`, implying even broader and more complex execution capabilities.
While the skill advises searching for schemas and checking connections, the broad nature of these tools means that if the agent's input is compromised (e.g., via prompt injection), an attacker could potentially orchestrate a wide range of unauthorized actions within the Icims Talent Cloud, including managing connections, executing arbitrary operations, or performing bulk data manipulations. The skill itself does not implement safeguards against such misuse, relying on the agent's input sanitization and the underlying Rube MCP system's security. Implement robust input validation and sanitization for any user-provided data that influences `tool_slug`, `arguments`, or connection parameters passed to these Rube tools. Consider implementing an allow-list for specific tool slugs or operations if the agent's scope should be limited. Ensure the agent's environment strictly controls access to and interpretation of `RUBE_MANAGE_CONNECTIONS` output, especially authentication links, to prevent credential exposure or phishing. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/ecda1eec9a971156)
Powered by SkillShield