Audit History
otel-expert - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | 2026年7月6日 上午03:21 | No confirmed findings | 0 | No capability change |
| v8 | 2026年7月6日 上午03:21 | No confirmed findings | 0 | External commands |
| v7 | 2026年6月28日 上午08:36 | No confirmed findings | 0 | No capability change |
| v6 | 2026年1月21日 下午03:41 | No confirmed findings | 0 | External commands |
| v5 | 2026年1月16日 下午04:21 | No confirmed findings | 0 | No capability change |
| v4 | 2026年1月16日 下午04:21 | No confirmed findings | 0 | External commands Filesystem access |
| v3 | 2026年1月10日 上午09:54 | No confirmed findings | 0 | No capability change |
| v2 | 2026年1月10日 上午09:54 | No confirmed findings | 0 | No capability change |
| v1 | 2026年1月10日 上午09:54 | No confirmed findings | 0 | Baseline |
2026年7月6日 上午03:21
The six static findings are false positives caused by Markdown inline code and a fenced Grep example in SKILL.md. The skill only declares Read, Grep, and Glob tools and does not instruct shell execution, network access, or secret handling. No semantic prompt-injection or malicious intent was found.
Risk Factors
⚙️ External commands (6)
2026年7月6日 上午03:21
The six static findings are false positives caused by Markdown inline code and a fenced Grep example in SKILL.md. The skill only declares Read, Grep, and Glob tools and does not instruct shell execution, network access, or secret handling. No semantic prompt-injection or malicious intent was found.
Risk Factors
⚙️ External commands (6)
2026年6月28日 上午08:36
Static analysis flagged markdown backticks, documentation paths, and possible weak cryptography keywords in SKILL.md. Manual review found these are false positives: the skill only instructs the assistant to read bundled OpenTelemetry docs and use allowed Read, Grep, and Glob tools. No prompt injection, network access, executable script, credential access, or malicious intent was found.
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.
2026年1月21日 下午03:41
This skill is a documentation helper that provides OpenTelemetry guidance from bundled docs. Static analysis flagged 17 patterns but all are false positives: hash fields in metadata, empty JSON arrays, and documentation examples with template variables. No actual security risks detected.
2026年1月16日 下午04:21
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
⚙️ External commands (6)
Detected Patterns
2026年1月16日 下午04:21
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
⚙️ External commands (6)
Detected Patterns
2026年1月10日 上午09:54
Pure prompt-based skill with read-only file access. No code execution, network calls, or file writing capabilities. Only uses Read, Grep, Glob tools to search bundled OpenTelemetry documentation.
Risk Factors
📁 Filesystem access (1)
2026年1月10日 上午09:54
Pure prompt-based skill with read-only file access. No code execution, network calls, or file writing capabilities. Only uses Read, Grep, Glob tools to search bundled OpenTelemetry documentation.
Risk Factors
📁 Filesystem access (1)
2026年1月10日 上午09:54
Pure prompt-based skill with read-only file access. No code execution, network calls, or file writing capabilities. Only uses Read, Grep, Glob tools to search bundled OpenTelemetry documentation.