Security Audit
dceoy/speckit-agent-skills:skills/speckit-taskstoissues
github.com/dceoy/speckit-agent-skillsTrust Assessment
dceoy/speckit-agent-skills:skills/speckit-taskstoissues received a trust score of 55/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized User Input to Shell Commands, Excessive Permissions: Direct Shell Command Execution.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on April 1, 2026 (commit a934d48e). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via Unsanitized User Input to Shell Commands The skill explicitly instructs the agent to run shell commands (`.specify/scripts/bash/check-prerequisites.sh` and `gh issue create`) and mentions handling user-provided arguments with specific escaping instructions (e.g., 'I'\''m Groot'). This indicates that user-controlled input will be incorporated into shell commands. If the agent or the underlying execution environment fails to properly sanitize or escape this input, an attacker could inject arbitrary shell commands. Specifically, task titles and bodies from `tasks.md` (an untrusted input) are used to create GitHub issues via a tool like `gh issue create`. If these strings are not thoroughly escaped before being passed as arguments to `gh issue create`, malicious content within `tasks.md` could lead to command execution. Implement robust input validation and sanitization for all user-provided data before it is used in shell commands. When constructing shell commands, always use parameterized execution or a library that handles proper escaping for the target shell. For `gh issue create`, ensure that task titles and bodies are strictly escaped or passed via standard input if the tool supports it, to prevent argument injection. | Static | SKILL.md:20 | |
| HIGH | Excessive Permissions: Direct Shell Command Execution The skill requires direct execution of arbitrary shell commands, including a local script (`.specify/scripts/bash/check-prerequisites.sh`), `git config`, and potentially `gh issue create`. This grants the agent broad access to the underlying system's command line interface. While necessary for the skill's functionality, this level of access, especially when combined with potential command injection vulnerabilities, poses a significant security risk. An attacker exploiting a command injection flaw could leverage these permissions to execute arbitrary code, access sensitive files, or modify the system. Minimize the scope of shell commands to only what is strictly necessary. If possible, use safer, higher-level APIs or libraries instead of direct shell execution. If shell execution is unavoidable, ensure that the commands are hardcoded or constructed with extreme care, and that the execution environment is sandboxed with minimal privileges. | Static | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/267941b1a6563d1a)
Powered by SkillShield