Trust Assessment
agent-router received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Potential Command Execution via LLM Instruction.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Execution via LLM Instruction The skill contains a direct instruction for the LLM to route 'Heavy coding' tasks to `codex exec`. This phrasing could be interpreted by the host LLM as an imperative command to execute or recommend the use of a command-line tool. If the LLM environment has access to a shell or a tool named `codex exec`, this could lead to command injection. Even if the LLM only outputs the command as a recommendation, it's a form of prompt injection that could lead to a user or another automated system executing an arbitrary command. Rephrase the instruction to clearly indicate that `codex exec` is a suggested action for a human user or an external system, rather than a command for the LLM to execute or directly invoke. For example, 'For heavy coding tasks, suggest the user utilize `codex exec`.' If tool invocation is intended, it should be done through a defined, sandboxed tool interface, not via direct instruction in markdown. | LLM | SKILL.md:30 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/sa9saq/agent-router/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/c502a9912e6e5fb9)
Powered by SkillShield