Trust Assessment
cats-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, 0 high, 1 medium, and 0 low severity. Key findings include Skill documents generic tool execution beyond stated scope.
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 | |
|---|---|---|---|---|
| MEDIUM | Skill documents generic tool execution beyond stated scope The skill `cats-automation` is described as automating 'Cats tasks' via Rube MCP. However, its documentation includes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. If `run_composio_tool()` allows execution of arbitrary Composio tools (not strictly limited to Cats-specific ones), this skill effectively provides access to a broader range of functionalities than implied by its name and primary description. An LLM using this skill might leverage this generic tool execution capability to perform actions outside the intended 'Cats automation' scope, leading to excessive permissions being exercised. Clarify the precise scope of `run_composio_tool()` within the context of this skill. If it is indeed generic, consider renaming the skill or adjusting its description to accurately reflect its broader capabilities. Alternatively, if possible, restrict the skill's access to `RUBE_REMOTE_WORKBENCH` or ensure `run_composio_tool()` is constrained to only Cats-related operations. | LLM | SKILL.md:65 |
Scan History
Embed Code
[](https://skillshield.io/report/75d09e5b5406ad75)
Powered by SkillShield