Audit History
azure-rbac - 5 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v5 Latest | Jul 23, 2026, 07:16 PM | No confirmed findings | 0 | No capability change |
| v4 | Jul 8, 2026, 09:36 AM | No confirmed findings | 0 | External commands |
| v3 | Jul 6, 2026, 06:10 PM | No confirmed findings | 0 | No capability change |
| v2 | Jun 30, 2026, 07:36 AM | No confirmed findings | 0 | No capability change |
| v1 | Feb 21, 2026, 08:39 AM | No confirmed findings | 0 | Baseline |
Jul 23, 2026, 07:16 PM
Both static findings are false positives caused by Markdown inline-code delimiters around an Azure permission name. The skill contains no executable shell or Ruby command at those locations.
Risk Factors
⚙️ External commands (2)
Jul 8, 2026, 09:36 AM
The two static findings are false positives caused by Markdown inline code around Azure permission names. No prompt injection, exfiltration intent, or executable command behavior was found in SKILL.md or version.json. The skill guides Azure RBAC role selection and assignment generation through named Azure tools.
Risk Factors
⚙️ External commands (2)
Jul 6, 2026, 06:10 PM
No static findings were reported for this prompt-only skill. Review of SKILL.md found no prompt injection, data exfiltration intent, or social engineering content.
Jun 30, 2026, 07:36 AM
Static analysis reported four high-severity weak cryptographic algorithm patterns, but review of SKILL.md found no cryptographic algorithms, hashing, encryption, or executable code. The alerts are false positives against Azure RBAC guidance text and tool names; no prompt injection or data exfiltration intent was found.
Static false positives ignored (4)
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.
Feb 21, 2026, 08:39 AM
Static analysis flagged 4 instances of 'Weak cryptographic algorithm' at SKILL.md lines 3 and 8. These are FALSE POSITIVES. Line 3 contains YAML syntax (description: >-) for multiline strings. Line 8 references Azure MCP tools (azure__documentation, azure__extension_cli_generate). The skill is a legitimate Microsoft Azure RBAC helper that recommends least-privilege roles and generates infrastructure code.