Audit History
bolder - 4 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v4 Latest | Jul 6, 2026, 07:58 PM | No confirmed findings | 0 | No capability change |
| v3 | Jul 6, 2026, 07:58 PM | No confirmed findings | 0 | No capability change |
| v2 | Jun 30, 2026, 11:06 AM | No confirmed findings | 0 | No capability change |
| v1 | Mar 16, 2026, 08:32 AM | No confirmed findings | 0 | Baseline |
Jul 6, 2026, 07:58 PM
Static findings are false positives caused by design vocabulary in SKILL.md. The skill provides frontend design guidance and shows no evidence of reconnaissance, exfiltration, prompt injection, or unsafe tool use.
Jul 6, 2026, 07:58 PM
Static findings are false positives caused by design vocabulary in SKILL.md. The skill provides frontend design guidance and shows no evidence of reconnaissance, exfiltration, prompt injection, or unsafe tool use.
Jun 30, 2026, 11:06 AM
Static analysis reported 21 potential issues in SKILL.md, mostly weak cryptography and reconnaissance labels. Manual review found design guidance only, with no executable code, command execution, filesystem access, network access, secret handling, or prompt injection attempt. The static matches are false positives caused by ordinary design vocabulary.
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.
Mar 16, 2026, 08:32 AM
Static analysis flagged 21 false positives related to the word 'bolder' being misidentified as 'blocker' and incorrectly categorized as weak cryptography. After manual review, the skill contains only instructional design documentation with no executable code, no network access, no file operations, and no security risks. All findings are dismissed as pattern-matching errors in a text-only design guidance skill.