Trust Assessment
linear received a trust score of 83/100, 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 Potential Arbitrary File Read via 'document create', Potential Arbitrary File Write via 'schema -o'.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Arbitrary File Read via 'document create' The skill describes the `linear document create --content-file` command, which allows specifying a local file to be uploaded as a document. If an AI agent uses this command and allows user-controlled input for the `--content-file` argument without proper sanitization, a malicious user could exploit this to read arbitrary files from the agent's filesystem (e.g., using path traversal like `../../../../etc/passwd`). This constitutes a data exfiltration risk. When constructing commands involving file paths from user input, ensure strict validation and sanitization to prevent path traversal. Consider using a dedicated file picker or restricting file access to a safe sandbox. | LLM | SKILL.md:109 | |
| MEDIUM | Potential Arbitrary File Write via 'schema -o' The skill describes the `linear schema -o` command, which allows specifying an output file path for the GraphQL schema. If an AI agent uses this command and allows user-controlled input for the output path without proper sanitization, a malicious user could exploit this to write to arbitrary locations on the agent's filesystem, potentially overwriting critical files or creating malicious ones. When constructing commands involving output file paths from user input, ensure strict validation and sanitization to prevent path traversal or writing to sensitive locations. Restrict output paths to a designated safe directory. | LLM | SKILL.md:124 |
Scan History
Embed Code
[](https://skillshield.io/report/59d6f63437dc3608)
Powered by SkillShield