Trust Assessment
agent-access-control 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 Unsanitized variable in HEREDOC leads to 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 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 | Unsanitized variable in HEREDOC leads to command injection The `AGENT_NAME` variable, passed as a command-line argument to `scripts/init-access-control.sh`, is directly interpolated into an unquoted HEREDOC block. This allows for shell command injection if an attacker can control the `AGENT_NAME` value. For example, if `AGENT_NAME` contains `$(malicious_command)`, `malicious_command` will be executed during the script's execution when the `access-control.json` file is created. To prevent shell command injection, quote the HEREDOC delimiter (e.g., `<< 'HEREDOC'`) to disable variable expansion within the block. Then, explicitly echo the `AGENT_NAME` variable with proper JSON escaping where needed. Alternatively, ensure the `AGENT_NAME` input is strictly validated to contain only safe characters, or generate the JSON file using a language/tool that handles escaping correctly. | LLM | scripts/init-access-control.sh:18 |
Scan History
Embed Code
[](https://skillshield.io/report/a4cad9a0cb93caa0)
Powered by SkillShield