Trust Assessment
anime received a trust score of 86/100, 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 Potential Command Injection via Unsanitized User Input in Skill Usage Instructions.
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 Unsanitized User Input in Skill Usage Instructions The `SKILL.md` documentation instructs the AI agent to execute shell commands (`./anime search "title"`, `./anime info <id>`) where parts of the command (`"title"`, `<id>`) are expected to be derived from user input. If the agent directly substitutes unsanitized user input into these shell commands, it creates a command injection vulnerability. An attacker could craft malicious input (e.g., `Frieren" && rm -rf / #`) to execute arbitrary commands on the host system. While the underlying `anime` script's implementation is not provided, the documented usage pattern itself describes a credible exploit path. The AI agent should rigorously sanitize and escape all user-provided input before constructing and executing shell commands. Alternatively, the `anime` script should be designed to parse arguments robustly, preventing shell injection, and the `SKILL.md` should explicitly warn about input sanitization or provide examples of safe command construction (e.g., using a library function that safely escapes shell arguments). | LLM | SKILL.md:58 |
Scan History
Embed Code
[](https://skillshield.io/report/3323f3100fa9f07f)
Powered by SkillShield