Audit History
github-issue-creator - 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, 11:58 PM | 1 confirmed | 0 | No capability change |
| v4 | Jul 8, 2026, 10:57 AM | No confirmed findings | 0 | No capability change |
| v3 | Jul 7, 2026, 01:01 AM | No confirmed findings | 0 | External commands Filesystem access |
| v2 | Jun 30, 2026, 03:56 PM | No confirmed findings | 1 | Filesystem access |
| v1 | Feb 25, 2026, 02:50 AM | No confirmed findings | 0 | Baseline |
Jul 23, 2026, 11:58 PM
All 13 static findings are false positives caused by Markdown code fences and inline code spans. No Ruby or shell command execution appears in SKILL.md. The skill requests repository file creation, creating a limited filesystem write risk.
Confirmed security concerns (1)
Risk Factors
Jul 8, 2026, 10:57 AM
The static findings are false positives caused by Markdown fences and inline code spans in SKILL.md. I found no Ruby execution, shell execution, prompt injection, network access, or malicious intent in the skill instructions.
Risk Factors
Jul 7, 2026, 01:01 AM
The external command detections are false positives caused by Markdown code fences and inline code examples in SKILL.md. I found no Ruby execution, shell command execution, prompt injection, network access, credential access, or malicious intent in the skill instructions.
Risk Factors
Jun 30, 2026, 03:56 PM
Static findings for Ruby shell backticks and weak cryptography are false positives caused by Markdown fences, Markdown examples, and .md naming text in SKILL.md. No malicious command execution, cryptographic code, exfiltration, or prompt injection evidence was found. The skill has low risk because it instructs the assistant to create issue Markdown files in an /issues/ directory.
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
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.
Risk Factors
📁 Filesystem access (1)
Feb 25, 2026, 02:50 AM
Static analyzer flagged 21 patterns as potential security issues, but all are false positives. The SKILL.md file contains only markdown documentation and prompt templates - no executable code. Backtick characters are used for markdown code blocks and inline code formatting, not shell command execution. No cryptographic functions or external command execution present.