Trust Assessment
githunt 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 Shell command injection via unquoted variable in command substitution.
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 | Shell command injection via unquoted variable in command substitution The `skills` variable, which is derived from user input (`$2`), is passed unquoted to `echo` within a command substitution. This allows an attacker to inject arbitrary shell commands by providing a specially crafted `skills` argument containing shell metacharacters (e.g., `;`, `|`, `&`). For example, an input like `githunt-search.sh berlin 'react; rm -rf /'` could lead to arbitrary command execution. To prevent command injection, use `printf "%s" "$skills"` instead of `echo "$skills"` to safely pass the variable's content to the pipe. A more robust solution would be to construct the JSON array using `jq` directly, for example: `skills_json=$(jq -nc --arg skills "$skills" '$skills | split(",")')`. | LLM | scripts/githunt-search.sh:30 |
Scan History
Embed Code
[](https://skillshield.io/report/9acba58f4b99ffbb)
Powered by SkillShield