Trust Assessment
tactical-ddd received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Skill contains direct instructions within untrusted content.
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 June 1, 2026 (commit 81e7e0dd). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Skill contains direct instructions within untrusted content The `SKILL.md` file, which is explicitly marked as untrusted input, contains direct operational instructions for the LLM. This violates the security principle that untrusted content should not dictate the LLM's behavior. Instructions such as 'Determine the user's intent first:', 'Load [detection.md](detection.md) and scan the target code', 'For each affected class, determine the correct building block:', and 'When reviewing code, report:' are present. These are attempts to inject commands into the LLM's processing flow from an untrusted source. Move all operational instructions, workflow definitions, and output formatting guidelines into a trusted part of the skill's definition (e.g., a dedicated configuration file or a trusted instruction block). The `SKILL.md` should only contain content to be processed or presented to the user, not instructions for the LLM's internal operation. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/baf27ab7888e8990)
Powered by SkillShield