Security Audit
dceoy/speckit-agent-skills:skills/speckit-clarify
github.com/dceoy/speckit-agent-skillsTrust Assessment
dceoy/speckit-agent-skills:skills/speckit-clarify 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 Insecure Shell Command Construction Instructions.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 8, 2026 (commit c21d8d2d). 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 | Insecure Shell Command Construction Instructions The skill instructs the agent on how to manually escape arguments for shell commands, explicitly suggesting the use of double quotes ("or double-quote if possible"). In shell environments, double quotes do not prevent the execution of command substitutions (e.g., `$(...)` or backticks). If the agent constructs a command using user input (such as a feature name) and wraps it in double quotes as suggested, an attacker could inject shell commands (e.g., `$(rm -rf /)`) that would be executed by the host. The instruction to manually handle escaping implies the agent is constructing raw shell strings rather than using safe argument passing (execv), creating a high risk of Command Injection. Remove instructions suggesting manual shell escaping or the use of double quotes for untrusted input. Explicitly instruct the agent to use safe, parameterized command execution methods (e.g., passing arguments as a list of strings) that do not involve shell interpretation, or strictly validate input to ensure it contains no shell metacharacters. | Unknown | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/f28d7208f62bf91e)
Powered by SkillShield