Trust Assessment
app-store-changelog received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Unquoted variable in shell command allows command injection.
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 14, 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 | |
|---|---|---|---|---|
| CRITICAL | Unquoted variable in shell command allows command injection The `scripts/collect_release_changes.sh` script constructs a `git` range (`${range}`) using user-supplied arguments (`$1`, `$2`). This variable is then used unquoted in `git log` commands. This allows an attacker to inject arbitrary shell commands by providing specially crafted input for `$1` or `$2`. For example, providing `v1.0; rm -rf /; #` as the first argument would execute `rm -rf /` on the system. Always quote variables when expanding them in shell commands, especially when they contain user-supplied input. Change `${range}` to `"${range}"` in both `git log` commands to ensure the range is treated as a single argument by `git` and prevent shell metacharacter interpretation. | LLM | scripts/collect_release_changes.sh:20 |
Scan History
Embed Code
[](https://skillshield.io/report/de6ad51ef2b98f4b)
Powered by SkillShield