Security Audit
dailybot-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
dailybot-automation received a trust score of 85/100, 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 Exposure of powerful 'RUBE_REMOTE_WORKBENCH' with 'run_composio_tool()'.
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 20, 2026 (commit 27904475). 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 | Exposure of powerful 'RUBE_REMOTE_WORKBENCH' with 'run_composio_tool()' The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The names 'workbench' and 'run_composio_tool()' strongly suggest a highly privileged and potentially general-purpose execution primitive. If `run_composio_tool()` allows the execution of arbitrary Composio tools or arbitrary code with user-controlled arguments, it could be exploited for command injection, data exfiltration, or unauthorized actions. The skill, by exposing this tool, grants excessive permissions to the LLM, increasing the attack surface. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary tool execution or code, consider restricting its scope or removing it if not strictly necessary for the skill's intended function. Ensure robust input validation and sandboxing for any arguments passed to `run_composio_tool()`. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/383b221779772418)
Powered by SkillShield