Security Audit
curated-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
curated-automation received a trust score of 89/100, 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, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned MCP dependency, Broad dynamic tool execution capabilities.
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 | |
|---|---|---|---|---|
| MEDIUM | Unpinned MCP dependency The skill manifest specifies a dependency on the 'rube' MCP without a version constraint. This means the skill will always use the latest version of the Rube MCP. If a future version introduces breaking changes, vulnerabilities, or malicious code, the skill could be negatively impacted without explicit review or update. Pin the Rube MCP dependency to a specific version or version range to ensure stability and security. For example, `{"mcp": ["rube@1.2.3"]}` or `{"mcp": ["rube@^1.0.0"]}` if the platform supports version ranges. | LLM | SKILL.md | |
| MEDIUM | Broad dynamic tool execution capabilities The skill promotes the use of `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` to dynamically discover and execute arbitrary operations within the 'curated' toolkit. This grants the agent broad access to all functionalities exposed by the `curated` toolkit via Rube MCP. The specific scope of 'Curated operations' is not defined within the skill, leading to potentially excessive and unconstrained permissions for the agent. If possible, restrict the `tool_slug` values that the agent is allowed to execute, or provide a more granular list of specific `curated` tools the skill is intended to use, rather than allowing arbitrary execution of any discovered tool. Clearly define the scope of 'Curated operations' and ensure the agent's access aligns with the principle of least privilege. | LLM | SKILL.md:50 |
Scan History
Embed Code
[](https://skillshield.io/report/b31059b5cc7e0b39)
Powered by SkillShield