审计历史
dispatching-parallel-agents - 8 审计
版本对比
各审计版本间的能力与发现变化，最新在前。
2026年7月6日 20:18
The detected external command findings are false positives caused by Markdown code fences and illustrative prompt examples in SKILL.md. The system and network reconnaissance findings are benign wording in a workflow checklist, and no prompt injection or malicious intent was found.
风险因素
2026年7月6日 20:18
The detected external command findings are false positives caused by Markdown code fences and illustrative prompt examples in SKILL.md. The system and network reconnaissance findings are benign wording in a workflow checklist, and no prompt injection or malicious intent was found.
风险因素
2026年6月30日 10:48
Static analysis reported command execution, weak crypto, system reconnaissance, and network reconnaissance patterns. AI review found no executable scripts, network calls, crypto code, or reconnaissance behavior; the matched lines are Markdown examples and checklist text. The skill is publishable with low risk because it only gives workflow guidance for coordinating AI agents.
已忽略静态误报 (4)
这些静态命中已被语义复核判定为误报，或只命中了 schema 定义里的词；这里保留展示用于透明度，但不影响质量评分。
2026年1月17日 07:31
Documentation-only skill containing markdown patterns for parallel agent dispatching. All 21 static findings are false positives: 7 from misidentified markdown code blocks, 8 from SHA256 hash values in JSON metadata, 2 from benign workflow descriptions, and 4 from over-sensitive keyword detection on documentation text. No executable code exists in this skill.
风险因素
⚙️ 外部命令 (4)
2026年1月17日 07:31
Documentation-only skill containing markdown patterns for parallel agent dispatching. All 21 static findings are false positives: 7 from misidentified markdown code blocks, 8 from SHA256 hash values in JSON metadata, 2 from benign workflow descriptions, and 4 from over-sensitive keyword detection on documentation text. No executable code exists in this skill.
风险因素
⚙️ 外部命令 (4)
2026年1月14日 00:02
Documentation-only skill containing markdown patterns for parallel agent dispatching. All 10 static findings are false positives: 7 from misidentified markdown code blocks, 1 from YAML frontmatter, 2 from benign workflow descriptions. No executable code exists in this skill.
风险因素
2026年1月6日 07:24
This is a pure documentation skill containing only markdown content. No executable code, scripts, network calls, filesystem access, environment variable reading, or external command execution. The skill teaches a parallel agent dispatching pattern.
2026年1月6日 07:24
This is a pure documentation skill containing only markdown content. No executable code, scripts, network calls, filesystem access, environment variable reading, or external command execution. The skill teaches a parallel agent dispatching pattern.