Audit History
agent-generation - 8 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v8 Latest | Jul 5, 2026, 07:15 AM | 1 confirmed | 0 | No capability change |
| v7 | Jul 5, 2026, 07:15 AM | 1 confirmed | 0 | Network access |
| v6 | Jun 29, 2026, 03:12 AM | 2 confirmed | 0 | Network access |
| v5 | Jan 16, 2026, 11:22 PM | No confirmed findings | 0 | No capability change |
| v4 | Jan 16, 2026, 11:22 PM | No confirmed findings | 0 | External commandsFilesystem access |
| v3 | Jan 10, 2026, 12:33 PM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 12:33 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 12:33 PM | No confirmed findings | 0 | Baseline |
Jul 5, 2026, 07:15 AM
The static backtick, reconnaissance, and device-file alerts are false positives from Markdown documentation and read-only analysis examples. No prompt injection or malicious exfiltration intent was found. The remaining concern is that generated agent templates grant broad write, shell, and network tools by default.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (115)
📁 Filesystem access (8)
Jul 5, 2026, 07:15 AM
The static backtick, reconnaissance, and device-file alerts are false positives from Markdown documentation and read-only analysis examples. No prompt injection or malicious exfiltration intent was found. The remaining concern is that generated agent templates grant broad write, shell, and network tools by default.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (115)
📁 Filesystem access (8)
Jun 29, 2026, 03:12 AM
Static analysis reported many command, filesystem, and weak-crypto patterns, but the weak-crypto findings are false positives from markdown words such as description and Design. The remaining risk is medium because the templates grant generated agents Bash, file editing, and web tools, and the analysis guide includes local enumeration commands for codebase inspection.
Confirmed security concerns (2)
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
⚙️ External commands (10)
📁 Filesystem access (6)
Detected Patterns
Jan 16, 2026, 11:22 PM
This is a documentation-only skill containing markdown files with templates and guidance for generating Claude Code agents. No executable code, no network calls, no file system access beyond reading documentation. The 306 static findings are false positives caused by the scanner misidentifying bash command examples in documentation as shell execution.
Risk Factors
⚙️ External commands (259)
📁 Filesystem access (8)
Jan 16, 2026, 11:22 PM
This is a documentation-only skill containing markdown files with templates and guidance for generating Claude Code agents. No executable code, no network calls, no file system access beyond reading documentation. The 306 static findings are false positives caused by the scanner misidentifying bash command examples in documentation as shell execution.
Risk Factors
⚙️ External commands (259)
📁 Filesystem access (8)
Jan 10, 2026, 12:33 PM
This is a documentation-only skill containing markdown files with templates and guidance for generating Claude Code agents. No executable code, no network calls, no file system access beyond reading documentation. Contains only conceptual content for agent design.
Jan 10, 2026, 12:33 PM
This is a documentation-only skill containing markdown files with templates and guidance for generating Claude Code agents. No executable code, no network calls, no file system access beyond reading documentation. Contains only conceptual content for agent design.
Jan 10, 2026, 12:33 PM
This is a documentation-only skill containing markdown files with templates and guidance for generating Claude Code agents. No executable code, no network calls, no file system access beyond reading documentation. Contains only conceptual content for agent design.