Trust Assessment
switch-modes received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via User-Controlled Configuration.
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 13, 2026 (commit 13146e6a). 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 | Potential Command Injection via User-Controlled Configuration The skill explicitly instructs the agent to use a shell command (`cat`) to read a user-controlled configuration file (`~/.openclaw/workspace/switch-modes.json`). The content of this file, specifically the 'model-id' values, is provided by the user during the '/modes setup' phase. These user-provided model IDs are then used to 'Update OpenClaw config' (`~/.openclaw/openclaw.json`). If the agent's implementation of updating the `openclaw.json` file involves shell commands (e.g., `sed`, `jq` without proper argument passing, or direct string interpolation into a shell command), a malicious user could inject arbitrary shell commands by crafting a model ID like `"; rm -rf / --no-preserve-root #"`. Avoid direct shell execution for parsing and modifying JSON files. Use robust programming language libraries (e.g., Python's `json` module) to safely read, parse, and write configuration files. If shell commands are absolutely necessary, ensure all user-controlled input is properly sanitized or passed as arguments to commands that handle them safely (e.g., `jq --arg` syntax). Implement strict validation for user-provided model IDs to ensure they conform to expected formats and do not contain shell metacharacters. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/464f23025800ff36)
Powered by SkillShield