Trust Assessment
grill 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, Path Traversal via User-Controlled Increment ID in Read Tool 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 15, 2026 (commit 1823c3f6). 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 | Path Traversal via User-Controlled Increment ID in Read Tool Instruction The skill instructs the LLM to use the 'Read' tool with a file path that incorporates a user-provided 'increment-id'. If the LLM does not sanitize this 'increment-id' for path traversal sequences (e.g., '..', '/', or absolute paths), an attacker could potentially manipulate the input to read arbitrary files within the filesystem scope accessible to the 'Read' tool. This poses a significant data exfiltration risk. Instruct the LLM to strictly sanitize the 'increment-id' before constructing file paths. Ensure it only contains valid characters for a simple identifier (e.g., alphanumeric, hyphens) and explicitly disallow path traversal sequences like '..' or '/' characters. Alternatively, the 'Read' tool's implementation should inherently prevent path traversal. | LLM | SKILL.md:48 | |
| 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 | plugins/specweave/skills/grill/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/d36127f4a76bf306)
Powered by SkillShield