Trust Assessment
agent-task-manager received a trust score of 70/100, 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 Arbitrary command execution via eval in cooldown.sh.
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 | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution via eval in cooldown.sh The `cooldown.sh` script uses `eval "$COMMAND"` to execute a command provided as a command-line argument. The `$COMMAND` variable is populated directly from user input (`$@` after `shift 2`). This allows an attacker to inject and execute arbitrary shell commands on the host system, leading to remote code execution. Replace `eval "$COMMAND"` with a safer method of execution that does not interpret the command string as arbitrary shell code. Consider using a whitelist of allowed commands and arguments, or execute the command and its arguments as a list using `exec` or a Python `subprocess` call, ensuring no shell interpretation of user-controlled input. | LLM | scripts/cooldown.sh:30 |
Scan History
Embed Code
[](https://skillshield.io/report/74386f5464dfc5e2)
Powered by SkillShield