Audit History
emergency-card - 7 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v7 Latest | Jul 5, 2026, 02:46 PM | 1 confirmed | 1 | No capability change |
| v6 | Jul 5, 2026, 02:46 PM | 1 confirmed | 1 | Filesystem access |
| v5 | Jun 30, 2026, 03:35 AM | No confirmed findings | 2 | Filesystem access |
| v4 | Jan 17, 2026, 06:13 AM | No confirmed findings | 0 | No capability change |
| v3 | Jan 17, 2026, 06:13 AM | No confirmed findings | 0 | External commandsNetwork access |
| v2 | Jan 5, 2026, 08:27 AM | No confirmed findings | 0 | No capability change |
| v1 | Jan 5, 2026, 08:27 AM | No confirmed findings | 0 | Baseline |
Jul 5, 2026, 02:46 PM
Most static external-command findings are false positives from fenced Markdown and JavaScript examples. One bash example that runs a local Python generator is confirmed as an external command risk. No prompt injection was found, and one medium semantic finding covers sensitive health data export risk.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
🌐 Network access (1)
⚙️ External commands (30)
Jul 5, 2026, 02:46 PM
Most static external-command findings are false positives from fenced Markdown and JavaScript examples. One bash example that runs a local Python generator is confirmed as an external command risk. No prompt injection was found, and one medium semantic finding covers sensitive health data export risk.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
🌐 Network access (1)
⚙️ External commands (30)
Jun 30, 2026, 03:35 AM
Static command, weak-crypto, and obfuscation alerts were reviewed in context and are mostly false positives from Markdown code fences, multilingual text, sample JSON, and example shell commands. The confirmed risk is privacy exposure because the skill reads local health files and creates portable cards, QR payloads, and optional network-dependent sharing paths for sensitive medical information.
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Static false positives ignored (2)
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
📁 Filesystem access (3)
⚙️ External commands (2)
🌐 Network access (4)
Detected Patterns
Jan 17, 2026, 06:13 AM
Pure documentation skill containing only markdown files with prompt instructions. No executable code, network calls, file system access, or external dependencies. The file I/O patterns shown are pseudocode examples for Claude prompts, not actual file system operations. All 119 static findings are false positives caused by the scanner misinterpreting documentation backticks and placeholders as security issues.
Risk Factors
⚙️ External commands (105)
🌐 Network access (1)
Jan 17, 2026, 06:13 AM
Pure documentation skill containing only markdown files with prompt instructions. No executable code, network calls, file system access, or external dependencies. The file I/O patterns shown are pseudocode examples for Claude prompts, not actual file system operations. All 119 static findings are false positives caused by the scanner misinterpreting documentation backticks and placeholders as security issues.
Risk Factors
⚙️ External commands (105)
🌐 Network access (1)
Jan 5, 2026, 08:27 AM
Pure documentation skill containing only markdown files with prompt instructions. No executable code, network calls, file system access, or external dependencies. The file I/O patterns shown are pseudocode examples for Claude prompts, not actual file system operations.
Jan 5, 2026, 08:27 AM
Pure documentation skill containing only markdown files with prompt instructions. No executable code, network calls, file system access, or external dependencies. The file I/O patterns shown are pseudocode examples for Claude prompts, not actual file system operations.