Audit History
algorithmic-art - 13 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v13 Latest | Jul 9, 2026, 08:23 AM | No confirmed findings | 5 | No capability change |
| v12 | Jul 9, 2026, 08:23 AM | No confirmed findings | 5 | No capability change |
| v11 | Jul 9, 2026, 05:49 AM | No confirmed findings | 5 | No capability change |
| v10 | Jul 9, 2026, 01:19 AM | No confirmed findings | 5 | No capability change |
| v9 | Jul 7, 2026, 05:56 PM | No confirmed findings | 5 | No capability change |
| v8 | Jul 6, 2026, 02:25 AM | No confirmed findings | 5 | No capability change |
| v7 | Jul 6, 2026, 02:25 AM | No confirmed findings | 5 | External commands |
| v6 | Jun 28, 2026, 08:22 AM | No confirmed findings | 0 | External commands |
| v5 | Jan 16, 2026, 03:21 PM | No confirmed findings | 0 | No capability change |
| v4 | Jan 16, 2026, 03:21 PM | No confirmed findings | 0 | Network accessExternal commandsContains scripts |
| v3 | Jan 4, 2026, 04:19 PM | No confirmed findings | 0 | No capability change |
| v2 | Jan 4, 2026, 04:19 PM | No confirmed findings | 0 | No capability change |
| v1 | Jan 4, 2026, 04:19 PM | No confirmed findings | 0 | Baseline |
Jul 9, 2026, 08:23 AM
The audit confirms low-severity network dependencies for p5.js and Google Fonts in the template and example instructions. All static external-command, script-execution, and reconnaissance findings are false positives from markdown fences, ordinary wording, or a JavaScript regex match.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 9, 2026, 08:23 AM
The audit confirms low-severity network dependencies for p5.js and Google Fonts in the template and example instructions. All static external-command, script-execution, and reconnaissance findings are false positives from markdown fences, ordinary wording, or a JavaScript regex match.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 9, 2026, 05:49 AM
Manual review confirmed only low-severity external network dependencies for p5.js and Google Fonts in the HTML template. The command execution, script execution, and reconnaissance alerts are false positives from Markdown code fences, inline code, prose, and JavaScript RegExp use. No prompt injection or hidden malicious behavior was found.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 9, 2026, 01:19 AM
The reviewed findings are mostly static-analysis false positives from Markdown code fences, prose, and RegExp.exec usage. The only confirmed issues are low-severity third-party network dependencies for p5.js and Google Fonts in the generated viewer template.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 7, 2026, 05:56 PM
The static execution and reconnaissance findings are false positives caused by markdown code fences, inline filenames, creative terminology, CSS names, and JavaScript regex matching. The only confirmed issues are low-risk hardcoded CDN dependencies for p5.js and Google Fonts in browser artifacts.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 6, 2026, 02:25 AM
Static findings were reviewed against the cited files. Most alerts are false positives from markdown code fences, normal JavaScript regex use, and generative art wording; the confirmed issues are low-severity external network dependencies for p5.js and Google Fonts.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jul 6, 2026, 02:25 AM
Static findings were reviewed against the cited files. Most alerts are false positives from markdown code fences, normal JavaScript regex use, and generative art wording; the confirmed issues are low-severity external network dependencies for p5.js and Google Fonts.
Capability review items (5)
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 (14)
🌐 Network access (5)
⚡ Contains scripts (1)
Jun 28, 2026, 08:22 AM
This official Anthropic skill is safe to publish. Static findings are expected for browser-based p5.js templates and CDN links, not malicious behavior. No prompt injection, filesystem access, credential handling, or command execution was found in the reviewed files.
Risk Factors
🌐 Network access (5)
⚡ Contains scripts (3)
Jan 16, 2026, 03:21 PM
Official skill from Anthropic's skills repository containing only frontend HTML/CSS/JavaScript code. Static analysis found zero risk factors, dangerous patterns, or security findings across 6 files and 1675 lines of code. The skill generates self-contained HTML artifacts using p5.js from CDN with no server-side operations.
Risk Factors
🌐 Network access (7)
⚙️ External commands (14)
⚡ Contains scripts (1)
Jan 16, 2026, 03:21 PM
Official skill from Anthropic's skills repository containing only frontend HTML/CSS/JavaScript code. Static analysis found zero risk factors, dangerous patterns, or security findings across 6 files and 1675 lines of code. The skill generates self-contained HTML artifacts using p5.js from CDN with no server-side operations.
Risk Factors
🌐 Network access (7)
⚙️ External commands (14)
⚡ Contains scripts (1)
Jan 4, 2026, 04:19 PM
Official skill from Anthropic's skills repository. Contains only frontend HTML/CSS/JavaScript code for generative art creation with p5.js. No security risks detected.
Jan 4, 2026, 04:19 PM
Official skill from Anthropic's skills repository. Contains only frontend HTML/CSS/JavaScript code for generative art creation with p5.js. No security risks detected.
Jan 4, 2026, 04:19 PM
Official skill from Anthropic's skills repository. Contains only frontend HTML/CSS/JavaScript code for generative art creation with p5.js. No security risks detected.