Trust Assessment
promptify 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 Potential Command Injection via `pbcopy` output.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via `pbcopy` output The skill explicitly instructs the execution of `echo 'PROMPT' | pbcopy` as part of its output process. If the `PROMPT` variable, which represents the optimized prompt, can be influenced by untrusted user input or contains shell metacharacters due to an oversight in the optimization logic, it could lead to arbitrary command execution on the host system. For example, a malicious prompt could be crafted to include commands like `$(rm -rf /)` which would then be executed by the shell. Sanitize the `PROMPT` variable to escape or remove any shell metacharacters before it is passed to `echo` for `pbcopy`. A safer alternative would be to use a platform-agnostic method for copying to the clipboard that does not rely on shell execution, or ensure that the environment where this skill runs has `pbcopy` sandboxed to prevent arbitrary command execution. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/a2f5685542c352a8)
Powered by SkillShield