Audit History
when-reviewing-pull-request-orchestrate-comprehensive-code-revie - 8 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v8 Latest | 2026年7月5日 下午01:55 | 1 confirmed | 0 | No capability change |
| v7 | 2026年7月5日 下午01:55 | 1 confirmed | 0 | Env variables Network access |
| v6 | 2026年6月29日 下午08:41 | 1 confirmed | 2 | Network access Env variables |
| v5 | 2026年1月17日 上午04:42 | No confirmed findings | 0 | No capability change |
| v4 | 2026年1月17日 上午04:42 | No confirmed findings | 0 | Filesystem accessExternal commandsEnv variables |
| v3 | 2026年1月10日 下午01:33 | No confirmed findings | 0 | No capability change |
| v2 | 2026年1月10日 下午01:33 | No confirmed findings | 0 | No capability change |
| v1 | 2026年1月10日 下午01:33 | No confirmed findings | 0 | Baseline |
2026年7月5日 下午01:55
The static findings are false positives caused by Markdown formatting and illustrative Bash examples rather than hidden executable code. No prompt injection or secret exfiltration intent was found. The main security concern is semantic: the workflow includes GitHub commands that can approve, label, comment on, and merge pull requests, including an admin merge example.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (171)
📁 Filesystem access (5)
🔑 Env variables (1)
2026年7月5日 下午01:55
The static findings are false positives caused by Markdown formatting and illustrative Bash examples rather than hidden executable code. No prompt injection or secret exfiltration intent was found. The main security concern is semantic: the workflow includes GitHub commands that can approve, label, comment on, and merge pull requests, including an admin merge example.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (171)
📁 Filesystem access (5)
🔑 Env variables (1)
2026年6月29日 下午08:41
Static analysis reported many high-risk patterns, but most are false positives caused by markdown examples, sample findings, and Graphviz labels rather than executable hidden code. The remaining risk is moderate: copyable shell snippets run project commands, call GitHub CLI, and build temporary file paths from PR inputs.
Confirmed security concerns (1)
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 (1)
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 (5)
📁 Filesystem access (3)
🌐 Network access (3)
Detected Patterns
2026年1月17日 上午04:42
Pure documentation SOP skill containing only workflow definitions and process documentation. No executable code exists. All flagged 'command' and 'credential' patterns are documentation examples showing standard dev tools (npm, gh, claude-flow) for legitimate code review automation.
Risk Factors
📁 Filesystem access (5)
⚙️ External commands (177)
🔑 Env variables (1)
2026年1月17日 上午04:42
Pure documentation SOP skill containing only workflow definitions and process documentation. No executable code exists. All flagged 'command' and 'credential' patterns are documentation examples showing standard dev tools (npm, gh, claude-flow) for legitimate code review automation.
Risk Factors
📁 Filesystem access (5)
⚙️ External commands (177)
🔑 Env variables (1)
2026年1月10日 下午01:33
Pure documentation skill containing only SOP workflow definitions and process documentation. No executable code, scripts, or concerning capabilities. All referenced commands (npm, gh, npx claude-flow) are standard development tools used by the user.
2026年1月10日 下午01:33
Pure documentation skill containing only SOP workflow definitions and process documentation. No executable code, scripts, or concerning capabilities. All referenced commands (npm, gh, npx claude-flow) are standard development tools used by the user.
2026年1月10日 下午01:33
Pure documentation skill containing only SOP workflow definitions and process documentation. No executable code, scripts, or concerning capabilities. All referenced commands (npm, gh, npx claude-flow) are standard development tools used by the user.