📦

Audit History

Project Setup & Architecture - 13 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v13 LatestJul 18, 2026, 10:17 AM No confirmed findings0No capability change
v12 Jul 17, 2026, 10:30 AM No confirmed findings0No capability change
v11 Jul 17, 2026, 10:30 AM No confirmed findings0No capability change
v10 Jul 17, 2026, 10:30 AM No confirmed findings0No capability change
v9 Jul 5, 2026, 05:02 AM No confirmed findings0No capability change
v8 Jul 5, 2026, 05:02 AM No confirmed findings0No capability change
v7 Jun 28, 2026, 01:07 PM No confirmed findings2External commandsNetwork access
v6 Jan 21, 2026, 05:02 PM No confirmed findings0 Network accessExternal commands
v5 Jan 16, 2026, 05:12 PM No confirmed findings0No capability change
v4 Jan 16, 2026, 05:12 PM No confirmed findings0Network accessExternal commands
v3 Jan 10, 2026, 10:58 AM No confirmed findings0No capability change
v2 Jan 10, 2026, 10:58 AM No confirmed findings0No capability change
v1 Jan 10, 2026, 10:58 AM No confirmed findings0Baseline

Jul 18, 2026, 10:17 AM

All 37 static findings are false positives caused by Markdown code formatting, visible documentation links, a local SQLite example, and a platform test checklist. The skill is a transparent React Native and Expo setup guide with no prompt injection, data-exfiltration intent, or concealed behavior found.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:30 AM

All 37 static findings are false positives caused by Markdown fences, documented development commands, a local SQLite example, or official documentation links. The skill contains no executable payload, data-exfiltration behavior, prompt injection attempt, or suspicious intent.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:30 AM

All 37 static findings are false positives caused by Markdown fences, documented development commands, a local SQLite example, or official documentation links. The skill contains no executable payload, data-exfiltration behavior, prompt injection attempt, or suspicious intent.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:30 AM

All 37 static findings are false positives caused by Markdown fences, documented development commands, a local SQLite example, or official documentation links. The skill contains no executable payload, data-exfiltration behavior, prompt injection attempt, or suspicious intent.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 5, 2026, 05:02 AM

The static findings are false positives caused by Markdown code fences, visible setup commands, documentation links, and a sample local SQLite filename. No prompt injection, malicious intent, credential access, exfiltration, or hidden network behavior was found in SKILL.md. Because the workflow includes package and migration commands, users should still review commands before execution.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: codex

Jul 5, 2026, 05:02 AM

The static findings are false positives caused by Markdown code fences, visible setup commands, documentation links, and a sample local SQLite filename. No prompt injection, malicious intent, credential access, exfiltration, or hidden network behavior was found in SKILL.md. Because the workflow includes package and migration commands, users should still review commands before execution.

1
Files scanned
194
Lines analyzed
2
Review items
0
False positives ignored
Audited by: codex

Jun 28, 2026, 01:07 PM

The static analyzer flagged many high-risk patterns, but review shows the content is a Markdown setup guide rather than executable code. The critical heuristic, weak cryptography, SQLite, reconnaissance, and documentation URL alerts are false positives, while package manager and npx setup commands are legitimate but require user awareness.

1
Files scanned
194
Lines analyzed
4
Review items
1
False positives ignored
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.

Medium
Package Manager And Project Setup Commands
The skill instructs assistants to run npm, npx, Expo CLI, mkdir, touch, Jest, ESLint, TypeScript, and Drizzle commands. These are expected for a project setup skill, but package installation and CLI execution can download dependencies, run lifecycle scripts, and modify the project workspace.
The commands are explicitly documented and are relevant to the stated setup purpose. Risk comes from normal package manager behavior, not from evidence of malicious intent.
Low
Benign Documentation Links And Local Database Example
The hardcoded URLs point to Expo documentation, and the SQLite string is a local example database name. The weak cryptography, system reconnaissance, and dangerous combination alerts are not supported by the reviewed content.
The cited lines contain a local SQLite filename, an app verification checklist item, and official documentation links. I found no credential access, exfiltration endpoint, weak cryptographic implementation, or obfuscated 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.

Low
Static Analyzer False Positives In Markdown Examples
The reported Ruby or shell backtick execution locations are Markdown code fences and code examples, not Ruby backtick execution. They do document shell commands, but there is no hidden script, obfuscation, or command injection path in the skill file.
The flagged text is visibly contained in Markdown fences and checklist examples. No executable wrapper or dynamic evaluation mechanism is present in the reviewed file.

Detected Patterns

External Package Installation Commands
Audited by: codex

Jan 21, 2026, 05:02 PM

This skill is a documentation guide for React Native and Expo project setup. All 55 static findings are false positives: URLs are documentation links, backticks are markdown code blocks, and commands are example snippets for users to run. No executable code, network access, or security risks detected. Safe for publication.

2
Files scanned
792
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 16, 2026, 05:12 PM

AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.

2
Files scanned
371
Lines analyzed
2
Review items
0
False positives ignored

Detected Patterns

Hardcoded URLWeak cryptographic algorithmRuby/shell backtick executionSQLite database fileSystem reconnaissance[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access[HEURISTIC] SUSPICIOUS COMBINATION: Filesystem + Credentials + Network
Audited by: claude

Jan 16, 2026, 05:12 PM

AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.

2
Files scanned
371
Lines analyzed
2
Review items
0
False positives ignored

Detected Patterns

Hardcoded URLWeak cryptographic algorithmRuby/shell backtick executionSQLite database fileSystem reconnaissance[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access[HEURISTIC] SUSPICIOUS COMBINATION: Filesystem + Credentials + Network
Audited by: claude

Jan 10, 2026, 10:58 AM

This is a pure markdown documentation skill containing no executable code. The file only provides guidance and templates for setting up React Native/Expo projects. No file system access, network calls, or code execution capabilities are present beyond reading the skill documentation itself.

1
Files scanned
194
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 10, 2026, 10:58 AM

This is a pure markdown documentation skill containing no executable code. The file only provides guidance and templates for setting up React Native/Expo projects. No file system access, network calls, or code execution capabilities are present beyond reading the skill documentation itself.

1
Files scanned
194
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 10, 2026, 10:58 AM

This is a pure markdown documentation skill containing no executable code. The file only provides guidance and templates for setting up React Native/Expo projects. No file system access, network calls, or code execution capabilities are present beyond reading the skill documentation itself.

1
Files scanned
194
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude