Security Audit
metaphor-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
metaphor-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 Broad tool execution capability via RUBE_MULTI_EXECUTE_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 | |
|---|---|---|---|---|
| MEDIUM | Broad tool execution capability via RUBE_MULTI_EXECUTE_TOOL The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` with `tool_slug: "TOOL_SLUG_FROM_SEARCH"`. This pattern allows the LLM to execute any tool discovered via `RUBE_SEARCH_TOOLS` within the Metaphor toolkit. While this is the intended automation pattern, it means the LLM is granted broad, unconstrained access to all functionalities exposed by the Metaphor toolkit. If the Metaphor toolkit includes tools with sensitive or destructive capabilities (e.g., data deletion, modification of critical settings, broad data access), this grants the LLM excessive permissions. An attacker who can influence the `use_case` parameter in `RUBE_SEARCH_TOOLS` could potentially guide the LLM to discover and execute harmful tools, leading to unintended actions or data manipulation. Implement stricter allow-lists or granular permission checks for specific tool slugs or categories that the LLM is permitted to execute. Ensure that `RUBE_SEARCH_TOOLS` results are filtered or validated to prevent discovery of overly sensitive tools for general LLM use, or require explicit human approval for high-risk operations. | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/c6d08534c72a49c9)
Powered by SkillShield