Trust Assessment
mastodon-scout 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 Search Query.
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 Search Query The skill instructs the AI agent to execute a shell command `mastodon-scout search <query>` where `<query>` is user-provided input. The skill definition does not include any explicit instructions for sanitizing or escaping this user input before it is passed to the shell. This omission creates a risk of command injection, where a malicious user could craft a query containing shell metacharacters (e.g., `'; rm -rf /'`) to execute arbitrary commands on the host system if the agent or the underlying execution environment does not automatically handle argument escaping. Modify the skill definition to explicitly instruct the AI agent to sanitize and properly escape the user-provided `<query>` before passing it to the `mastodon-scout` binary. This can be achieved by quoting the argument (e.g., `'{baseDir}/bin/mastodon-scout search "{query}"'`) or by using a safe command execution method that passes arguments as a list rather than a single string for shell interpretation. | LLM | SKILL.md:38 |
Scan History
Embed Code
[](https://skillshield.io/report/a6078eb1b9b4d229)
Powered by SkillShield