Trust Assessment
inference-sh received a trust score of 38/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 0 high, 0 medium, and 1 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Broad Bash Tool Permission for `infsh`.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/okaris/inference-sh/SKILL.md:9 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/okaris/inference-sh/SKILL.md:9 | |
| LOW | Broad Bash Tool Permission for `infsh` The skill declares `Bash(infsh *)` as an allowed tool. This grants the skill the ability to execute any command starting with `infsh`, including all current and future subcommands. While this aligns with the skill's stated purpose of interacting with the `inference.sh` CLI, it represents a broad permission that could be misused if the `infsh` CLI itself has vulnerabilities, or if the skill's prompts are manipulated to call dangerous `infsh` commands. A more granular permission set, if possible, would reduce the potential attack surface. Consider narrowing the `Bash` tool permission to only the specific `infsh` subcommands required by the skill (e.g., `Bash(infsh app run, infsh app list, infsh task get, infsh login)`). Regularly review the `infsh` CLI documentation for any potentially dangerous subcommands. | LLM | Manifest |
Scan History
Embed Code
[](https://skillshield.io/report/bb1d90650cdb7073)
Powered by SkillShield