Trust Assessment
wyld-stallyns received a trust score of 95/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Potential for arbitrary code execution or file manipulation via 'summon forge' command.
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 | |
|---|---|---|---|---|
| MEDIUM | Potential for arbitrary code execution or file manipulation via 'summon forge' command The skill defines a `summon forge <candidate>` command which is described as creating a new legend. The 'File Locations' section indicates that 'Legend modules' are stored in `assets/legends/`. If the `<candidate>` input is used to create or modify files within `assets/legends/` without proper sanitization, and these 'modules' are later loaded and executed as code, this could lead to arbitrary code execution (Command Injection). Even if not directly executed, uncontrolled file writes based on user input could lead to data corruption or other system compromises. The skill's description implies write access to `assets/legends/` for this operation, which could be an excessive permission if not carefully managed. The exact implementation details are not provided in this `SKILL.md` file, but the described functionality presents a common vulnerability pattern. Implement robust input validation and sanitization for the `<candidate>` argument in the `summon forge` command. Ensure that any created 'legend modules' are treated as data, not executable code, or are executed within a strictly sandboxed environment. Restrict file system write permissions to the absolute minimum necessary and prevent user input from influencing file paths or directly injecting into executable content. The `FORGE.md` protocol should detail these security measures. | LLM | SKILL.md:105 |
Scan History
Embed Code
[](https://skillshield.io/report/47a59ddbd0637263)
Powered by SkillShield