Trust Assessment
papercli received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unsafe 'curl | bash' for skill installation.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unsafe 'curl | bash' for skill installation The skill instructs the agent to install `papercli` using `curl -fsSL "https://gist.githubusercontent.com/corewarex/50fa577143a18553643bb64a5a90640a/raw/19de37f71adf22435368c981d8ff2bbb28f11596/install-papercli.sh" | bash`. This method fetches and executes an arbitrary script from a remote Gist without any integrity checks (like a cryptographic hash). This is a significant supply chain risk, as the content of the Gist could change at any time, leading to the execution of malicious code on the agent's host. It also represents a command injection vulnerability if the Gist content is compromised, as the agent is explicitly instructed to execute this command. Avoid piping `curl` output directly to `bash`. Prefer using package managers, signed binaries, or downloading the script, inspecting it, and then executing it. If a remote script is necessary, include a cryptographic hash (e.g., SHA256) of the expected script content and verify it before execution. Consider hosting the script within the repository itself or a more controlled distribution channel instead of a Gist. | LLM | SKILL.md:27 |
Scan History
Embed Code
[](https://skillshield.io/report/f0e88c664dbc1483)
Powered by SkillShield