Security Audit
Mistral AI Automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
Mistral AI Automation received a trust score of 83/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Potential Data Exfiltration via Broad File Access, Unpinned Dependency in Manifest.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Data Exfiltration via Broad File Access The skill exposes `MISTRAL_AI_LIST_FILES` and `MISTRAL_AI_DOWNLOAD_FILE` tools. `MISTRAL_AI_LIST_FILES` allows browsing 'uploaded files' and `MISTRAL_AI_DOWNLOAD_FILE` allows downloading 'raw binary content of a previously uploaded file' using a `file_id` obtained from `LIST_FILES`. The skill description does not specify any scope limitations (e.g., 'only files uploaded by the current user'). If the underlying Mistral AI API or Composio platform does not strictly enforce user/tenant-specific access controls, a compromised agent or malicious user could potentially list and download files belonging to other users or sensitive system files, leading to unauthorized data exfiltration. Ensure that `MISTRAL_AI_LIST_FILES` and `MISTRAL_AI_DOWNLOAD_FILE` strictly enforce authorization policies, allowing access only to files owned by the current user/tenant. Update the skill description to explicitly state these access limitations if they exist, or implement them if they don't. | LLM | SKILL.md:36 | |
| MEDIUM | Unpinned Dependency in Manifest The skill's manifest declares a dependency on `rube` via the Composio MCP server (`"mcp": ["rube"]`). However, no specific version is pinned. This means that if a new, potentially malicious or vulnerable version of `rube` is released and deployed to the MCP server, this skill could automatically pull and use it, introducing a supply chain risk. Pin the `rube` dependency to a specific, known-good version in the manifest (e.g., `"mcp": ["rube@1.2.3"]`) to prevent automatic updates to potentially vulnerable or malicious versions. Regularly review and update dependencies. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/7406edad9e5f9593)
Powered by SkillShield