Trust Assessment
video-prompting-guide received a trust score of 34/100, 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, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Broad Bash `infsh` tool access.
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/video-prompting-guide/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/video-prompting-guide/SKILL.md:9 | |
| MEDIUM | Broad Bash `infsh` tool access The skill declares `Bash(infsh *)` as an allowed tool, granting it permission to execute any command starting with `infsh`. While the provided skill content primarily serves as a guide and demonstrates `infsh app run` commands, this broad permission could allow an LLM to execute other `infsh` commands (e.g., `infsh config`, `infsh delete`, `infsh login`) if prompted to do so. For a skill that is largely informational, such extensive execution capabilities are excessive and increase the attack surface for potential command injection or unintended actions if the LLM were to dynamically construct `infsh` commands based on untrusted user input. Restrict `allowed-tools` to the minimum necessary `infsh` commands and arguments required for the skill's intended function. For a guide, consider removing Bash permissions entirely if no execution is strictly necessary, or narrow it down to specific subcommands like `Bash(infsh app run *)` if the skill is intended to demonstrate execution. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/cb293b6d831225b2)
Powered by SkillShield