Audit History
changelog-automation - 9 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v9 Latest | Jul 7, 2026, 06:43 AM | No confirmed findings | 0 | No capability change |
| v8 | Jul 7, 2026, 06:43 AM | No confirmed findings | 0 | No capability change |
| v7 | Jun 30, 2026, 10:19 PM | No confirmed findings | 2 | No capability change |
| v6 | Jun 30, 2026, 10:19 PM | No confirmed findings | 2 | External commandsNetwork accessEnv variables |
| v5 | Jan 21, 2026, 06:55 PM | No confirmed findings | 0 | Network accessExternal commandsEnv variables |
| v4 | Jan 17, 2026, 07:47 AM | No confirmed findings | 0 | No capability change |
| v3 | Jan 17, 2026, 07:47 AM | No confirmed findings | 0 | Network accessExternal commandsEnv variables |
| v2 | Jan 4, 2026, 04:51 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 4, 2026, 04:51 PM | No confirmed findings | 0 | Baseline |
Jul 7, 2026, 06:43 AM
Static findings are Markdown examples, reference links, and CI secret placeholders, not hidden executable code. I found no prompt injection, credential exfiltration, or malicious network behavior in SKILL.md.
Risk Factors
⚙️ External commands (42)
🌐 Network access (13)
🔑 Env variables (2)
Jul 7, 2026, 06:43 AM
Static findings are Markdown examples, reference links, and CI secret placeholders, not hidden executable code. I found no prompt injection, credential exfiltration, or malicious network behavior in SKILL.md.
Risk Factors
⚙️ External commands (42)
🌐 Network access (13)
🔑 Env variables (2)
Jun 30, 2026, 10:19 PM
Static analysis flagged many command, network, token, and weak-crypto patterns. Review found no malicious code or prompt injection; most flags are documentation examples, Markdown fences, URLs, and false positives from words such as description. The skill is publishable with warnings because it teaches release workflows that can push tags, create releases, and use GitHub or npm tokens.
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 (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
⚙️ External commands (4)
🌐 Network access (4)
🔑 Env variables (1)
Jun 30, 2026, 10:19 PM
Static analysis flagged many command, network, token, and weak-crypto patterns. Review found no malicious code or prompt injection; most flags are documentation examples, Markdown fences, URLs, and false positives from words such as description. The skill is publishable with warnings because it teaches release workflows that can push tags, create releases, and use GitHub or npm tokens.
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 (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
⚙️ External commands (4)
🌐 Network access (4)
🔑 Env variables (1)
Jan 21, 2026, 06:55 PM
This skill contains documentation and configuration templates for changelog automation tools. All static findings are false positives: network URLs are documentation references to keepachangelog.com and semver.org, backtick patterns are code examples in markdown format, and env_access references are configuration samples for GitHub Actions workflows. No executable code or security risks detected.
Jan 17, 2026, 07:47 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
🌐 Network access (13)
⚙️ External commands (43)
🔑 Env variables (3)
Detected Patterns
Jan 17, 2026, 07:47 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risk Factors
🌐 Network access (13)
⚙️ External commands (43)
🔑 Env variables (3)
Detected Patterns
Jan 4, 2026, 04:51 PM
Pure documentation skill containing only markdown templates and configuration examples. No executable code, no file access, no network calls, no command execution. The skill provides patterns that users apply manually to their own projects.
Jan 4, 2026, 04:51 PM
Pure documentation skill containing only markdown templates and configuration examples. No executable code, no file access, no network calls, no command execution. The skill provides patterns that users apply manually to their own projects.