Security Audit
mattpocock/skills:skills/in-progress/claude-handoff
github.com/mattpocock/skillsTrust Assessment
mattpocock/skills:skills/in-progress/claude-handoff received a trust score of 85/100, 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 Potential Command Injection via Unsanitized User Input in Shell Execution.
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 July 17, 2026 (commit 9603c1cc). 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 | Potential Command Injection via Unsanitized User Input in Shell Execution The skill instructs the LLM to execute a shell command (`claude --bg --name "<descriptive name>" "<handoff summary>"`) using dynamically generated values, including a user-provided argument ('What will the next session be used for?') and conversation summaries. If these inputs contain shell metacharacters (such as backticks, `$()`, or `;`), they can lead to arbitrary command execution in the user's terminal environment. Ensure that any command-line arguments generated from user input or LLM summaries are strictly sanitized, escaped, or passed via a secure API that does not invoke a shell interpreter directly. | LLM | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/25bb479cdb25efcc)
Powered by SkillShield