Audit History
learn-on - 6 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v6 Latest | 2026年7月4日 下午02:06 | No confirmed findings | 0 | No capability change |
| v5 | 2026年7月4日 下午02:06 | No confirmed findings | 0 | External commands |
| v4 | 2026年6月27日 下午01:07 | No confirmed findings | 0 | External commands |
| v3 | 2026年1月16日 下午01:02 | No confirmed findings | 0 | No capability change |
| v2 | 2026年1月16日 下午01:02 | No confirmed findings | 0 | External commands |
| v1 | 2026年1月10日 上午08:59 | No confirmed findings | 0 | Baseline |
2026年7月4日 下午02:06
All eight static findings are false positives caused by Markdown code formatting and slash-command references in SKILL.md. No prompt injection, data exfiltration intent, or executable command behavior was found in the reviewed file.
Risk Factors
⚙️ External commands (8)
2026年7月4日 下午02:06
All eight static findings are false positives caused by Markdown code formatting and slash-command references in SKILL.md. No prompt injection, data exfiltration intent, or executable command behavior was found in the reviewed file.
Risk Factors
⚙️ External commands (8)
2026年6月27日 下午01:07
AI review found that the static external command alerts are false positives from markdown backticks and fenced examples in SKILL.md. The weak cryptography alert is also a false positive on frontmatter description text, with no cryptographic code or algorithm usage 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16日 下午01:02
All 15 static findings are FALSE POSITIVES. This is a pure prompt-based skill with no executable code. It only reads/writes to its own local knowledge/state.json file within the skill directory. No network calls, no command execution, no external dependencies. The static scanner misidentified Markdown code formatting and JSON metadata as security patterns.
Risk Factors
⚙️ External commands (8)
2026年1月16日 下午01:02
All 15 static findings are FALSE POSITIVES. This is a pure prompt-based skill with no executable code. It only reads/writes to its own local knowledge/state.json file within the skill directory. No network calls, no command execution, no external dependencies. The static scanner misidentified Markdown code formatting and JSON metadata as security patterns.
Risk Factors
⚙️ External commands (8)
2026年1月10日 上午08:59
Pure prompt-based skill with no executable code. Only accesses local state file within skill's own directory. No network calls, no command execution, no external dependencies.