Trust Assessment
tdd-orchestrator 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 Broad 'Bash' tool permission declared.
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 | Broad 'Bash' tool permission declared The skill's manifest declares 'Bash' as an allowed tool. This grants the AI agent the ability to execute arbitrary shell commands on the host system, which is a highly privileged operation. While a TDD orchestrator might require running tests or interacting with the development environment, the broadness of 'Bash' allows for potential command injection and system compromise if the agent is manipulated. More granular tools or a restricted command execution environment would be preferable to mitigate this risk. Consider replacing 'Bash' with more specific tools for running tests (e.g., a 'run_tests' tool that only accepts predefined test commands) or implementing a sandboxed execution environment. If 'Bash' is strictly necessary, ensure robust input validation and sanitization for any commands passed to it by the agent. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/472234ffff9c3454)
Powered by SkillShield