Trust Assessment
wpds 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 Command Injection via Local Lint Scripts.
The analysis covered 4 layers: llm_behavioral_safety, manifest_analysis, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit cdc950d5). 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 | Command Injection via Local Lint Scripts The skill instructs the agent to execute 'lint scripts' found in the local context of a task. This can lead to command injection if the agent has shell execution capabilities. A malicious repository could define a 'lint' script in its package.json that executes arbitrary, harmful commands on the agent's host machine, potentially leading to data exfiltration, file system manipulation, or further system compromise. Remove the instruction to execute local scripts. Instead, the skill could instruct the agent to advise the user to run their own validation scripts after the code is generated. The agent should not be responsible for executing potentially untrusted code from the user's workspace. | Unknown | SKILL.md:46 |
Scan History
Embed Code
[](https://skillshield.io/report/1d834a17a6b0e68e)
Powered by SkillShield