Audit History
commit-prepare - 11 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v11 Latest | Jul 9, 2026, 01:34 AM | No confirmed findings | 0 | No capability change |
| v10 | Jul 9, 2026, 01:34 AM | No confirmed findings | 0 | No capability change |
| v9 | Jul 7, 2026, 11:11 PM | No confirmed findings | 6 | No capability change |
| v8 | Jul 5, 2026, 04:23 AM | No confirmed findings | 2 | No capability change |
| v7 | Jul 5, 2026, 04:23 AM | No confirmed findings | 2 | Network access |
| v6 | Jun 28, 2026, 06:03 PM | No confirmed findings | 2 | No capability change |
| v5 | Jan 16, 2026, 08:37 PM | No confirmed findings | 0 | No capability change |
| v4 | Jan 16, 2026, 08:37 PM | No confirmed findings | 0 | No capability change |
| v3 | Jan 10, 2026, 11:33 AM | No confirmed findings | 0 | No capability change |
| v2 | Jan 10, 2026, 11:33 AM | No confirmed findings | 0 | No capability change |
| v1 | Jan 10, 2026, 11:33 AM | No confirmed findings | 0 | Baseline |
Jul 9, 2026, 01:34 AM
The static findings are documentation examples for normal git commit preparation, not unsafe command execution or network behavior. The skill asks for confirmation before committing, warns against bypassing hooks, and includes a secrets check reminder. No prompt injection attempt or malicious intent was found.
Risk Factors
⚙️ External commands (39)
🌐 Network access (2)
Jul 9, 2026, 01:34 AM
The static findings are documentation examples for normal git commit preparation, not unsafe command execution or network behavior. The skill asks for confirmation before committing, warns against bypassing hooks, and includes a secrets check reminder. No prompt injection attempt or malicious intent was found.
Risk Factors
⚙️ External commands (39)
🌐 Network access (2)
Jul 7, 2026, 11:11 PM
Most static findings are Markdown backtick false positives around examples, commit templates, or attribution links. I confirmed limited external-command risk where the skill instructs staging and committing files, especially the heredoc command substitution for multi-line messages. No prompt injection or covert network behavior was found in SKILL.md.
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (39)
🌐 Network access (2)
Jul 5, 2026, 04:23 AM
The audit reviewed 41 static findings in SKILL.md. Most hits are Markdown code fences or inline examples, not executable Ruby backticks. The only retained issue is the multi-line commit template that uses shell command substitution.
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (39)
🌐 Network access (2)
Jul 5, 2026, 04:23 AM
The audit reviewed 41 static findings in SKILL.md. Most hits are Markdown code fences or inline examples, not executable Ruby backticks. The only retained issue is the multi-line commit template that uses shell command substitution.
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (39)
🌐 Network access (2)
Jun 28, 2026, 06:03 PM
Static analysis flagged many shell patterns because the skill documents git commands and commit-message examples. Review found no malicious intent, data exfiltration, prompt injection, or hidden execution path, but the skill does instruct agents to run repository-mutating git commands after user confirmation.
Capability review items (2)
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 (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.
Risk Factors
⚙️ External commands (5)
Detected Patterns
Jan 16, 2026, 08:37 PM
Pure prompt-based skill with no executable code. Only provides guidelines for generating conventional commit messages through git commands. All static findings are false positives: 'weak crypto' misidentifies 'conventional commits' standard, 'shell backtick' flags legitimate git command documentation, and URLs are standard attribution links. All git operations require user approval.
Risk Factors
⚙️ External commands (4)
Jan 16, 2026, 08:37 PM
Pure prompt-based skill with no executable code. Only provides guidelines for generating conventional commit messages through git commands. All static findings are false positives: 'weak crypto' misidentifies 'conventional commits' standard, 'shell backtick' flags legitimate git command documentation, and URLs are standard attribution links. All git operations require user approval.
Risk Factors
⚙️ External commands (4)
Jan 10, 2026, 11:33 AM
Pure prompt-based skill with no executable code. Only provides guidelines for generating conventional commit messages through git commands. No network, filesystem, or environment access beyond standard git operations required for commit message preparation.
Risk Factors
⚙️ External commands (3)
Jan 10, 2026, 11:33 AM
Pure prompt-based skill with no executable code. Only provides guidelines for generating conventional commit messages through git commands. No network, filesystem, or environment access beyond standard git operations required for commit message preparation.
Risk Factors
⚙️ External commands (3)
Jan 10, 2026, 11:33 AM
Pure prompt-based skill with no executable code. Only provides guidelines for generating conventional commit messages through git commands. No network, filesystem, or environment access beyond standard git operations required for commit message preparation.