Audit History
mcp-apps-builder - 4 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v4 Latest | Jul 6, 2026, 06:13 PM | No confirmed findings | 0 | No capability change |
| v3 | Jul 6, 2026, 06:13 PM | No confirmed findings | 0 | No capability change |
| v2 | Jun 30, 2026, 08:11 AM | No confirmed findings | 0 | Network accessExternal commandsFilesystem accessEnv variablesContains scripts |
| v1 | Feb 24, 2026, 08:58 AM | No confirmed findings | 0 | Baseline |
Jul 6, 2026, 06:13 PM
Static analysis reported many severe patterns, but contextual review found them in Markdown documentation, examples, relative links, and placeholder configuration. No confirmed malicious intent, credential exfiltration, prompt-injection attempt, or runnable hidden behavior was found. The main residual risk is that users may copy example commands, network calls, or environment variable handling without adapting them safely.
Risk Factors
⚙️ External commands (230)
🌐 Network access (50)
📁 Filesystem access (40)
🔑 Env variables (47)
⚡ Contains scripts (1)
Jul 6, 2026, 06:13 PM
Static analysis reported many severe patterns, but contextual review found them in Markdown documentation, examples, relative links, and placeholder configuration. No confirmed malicious intent, credential exfiltration, prompt-injection attempt, or runnable hidden behavior was found. The main residual risk is that users may copy example commands, network calls, or environment variable handling without adapting them safely.
Risk Factors
⚙️ External commands (230)
🌐 Network access (50)
📁 Filesystem access (40)
🔑 Env variables (47)
⚡ Contains scripts (1)
Jun 30, 2026, 08:11 AM
Static analysis reported many severe patterns, but contextual review found them in Markdown documentation, examples, relative links, and license text rather than executable skill code. No confirmed malicious intent, credential exfiltration, prompt-injection attempt, or runnable hidden behavior was found. The main residual risk is that users may copy example commands, network calls, environment variable handling, or development-only options without adapting them safely.
Static false positives ignored (6)
These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.
Risk Factors
🌐 Network access (3)
⚙️ External commands (3)
📁 Filesystem access (3)
🔑 Env variables (3)
⚡ Contains scripts (1)
Feb 24, 2026, 08:58 AM
All 1766 flagged patterns are false positives. The findings are in markdown documentation files (SKILL.md, references/*.md) containing code examples and tutorials. No executable code with security implications detected. This is a documentation/reference skill for mcp-use framework best practices.