Trust Assessment
qr-auction-bidder received a trust score of 88/100, 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 Shell Execution Examples.
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 | Potential Command Injection via Shell Execution Examples The skill documentation (`SKILL.md`) includes multiple `bash` code blocks demonstrating direct shell command execution using `curl` and a local script (`scripts/bankr.sh`). If the AI agent is designed to interpret and execute these examples, or to construct similar commands based on user input, there is a significant risk of command injection. Malicious user input, if not properly sanitized, could be interpolated into these commands, leading to arbitrary code execution on the host system. For instance, if a user-provided URL or name is directly inserted into the `createBid` or `contributeToBid` commands without escaping, it could allow an attacker to inject shell metacharacters. Implement robust input validation and sanitization for all user-provided data that might be used in constructing shell commands. Avoid direct interpolation of user input into shell commands. Prefer using dedicated libraries or APIs that handle command arguments securely. If direct shell execution is unavoidable, ensure commands are executed within a sandboxed environment with minimal privileges. Require explicit user confirmation for any command execution involving user-supplied parameters. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/526e0c3199463330)
Powered by SkillShield