Security Audit
amara-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
amara-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 Broad Access to External System Operations.
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 | Broad Access to External System Operations The skill provides the LLM with the capability to discover and execute any available Amara operation via the Rube MCP. This broad access, facilitated by `RUBE_SEARCH_TOOLS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`, means that a compromised LLM could perform unauthorized actions, modify data, or access sensitive information within Amara. While this is the intended functionality of the skill, it represents a significant security surface area. Implement fine-grained access control within the Rube MCP or Amara itself to restrict the scope of actions an LLM can perform. Alternatively, modify the skill's instructions to limit the `use_case` queries in `RUBE_SEARCH_TOOLS` to only necessary operations. Ensure robust prompt injection defenses are in place for the LLM to prevent malicious users from exploiting these broad capabilities. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/17c3c550b3590ae0)
Powered by SkillShield