Skills doc-sync Audit History
📦

Audit History

doc-sync - 9 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v9 LatestJul 23, 2026, 03:33 PM No confirmed findings0No capability change
v8 Jul 8, 2026, 02:30 AM No confirmed findings0No capability change
v7 Jul 5, 2026, 06:47 PM No confirmed findings0No capability change
v6 Jul 5, 2026, 06:47 PM No confirmed findings0No capability change
v5 Jun 30, 2026, 04:15 AM 1 confirmed0No capability change
v4 Jan 17, 2026, 06:37 AM No confirmed findings0No capability change
v3 Jan 17, 2026, 06:37 AM No confirmed findings0External commands
v2 Jan 4, 2026, 04:30 PM No confirmed findings0No capability change
v1 Jan 4, 2026, 04:30 PM No confirmed findings0Baseline

Jul 23, 2026, 03:33 PM

All 18 backtick findings are false positives caused by Markdown formatting or documented, read-only search and Git commands. The network-scanning finding is also false because nmap appears only as text inside a grep pattern.

1
Files scanned
276
Lines analyzed
1
Review items
0
False positives ignored
Audited by: codex

Jul 8, 2026, 02:30 AM

Static analysis flagged Markdown backticks, fenced shell examples, and an IdeaVim mapping search pattern. Review found no prompt injection, malware intent, credential access, network access, or data exfiltration behavior in SKILL.md.

1
Files scanned
276
Lines analyzed
1
Review items
0
False positives ignored
Audited by: codex

Jul 5, 2026, 06:47 PM

All static findings are false positives. The backtick detections are Markdown inline code or code fences, and the command examples are read-only local checks for documentation verification. The nmap hit is a Vim mapping function in a regex, not a network scanning tool.

1
Files scanned
276
Lines analyzed
1
Review items
1
False positives ignored
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.

High
Network scanning tools
grep -E 'fun \w+\(|nmap\(|vmap\(|map\(' doc/*.md -B1 -A3
Force-confirmed blocker/high static finding; AI dismissal overridden.
Audited by: codex

Jul 5, 2026, 06:47 PM

All static findings are false positives. The backtick detections are Markdown inline code or code fences, and the command examples are read-only local checks for documentation verification. The nmap hit is a Vim mapping function in a regex, not a network scanning tool.

1
Files scanned
276
Lines analyzed
1
Review items
1
False positives ignored
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.

High
Network scanning tools
grep -E 'fun \w+\(|nmap\(|vmap\(|map\(' doc/*.md -B1 -A3
Force-confirmed blocker/high static finding; AI dismissal overridden.
Audited by: codex

Jun 30, 2026, 04:15 AM

The confirmed risk is legitimate but elevated command guidance: the skill directs the assistant to run grep, find, and git commands while auditing documentation. The static weak-cryptography and network-scanning alerts are false positives from words such as description and Vim mapping syntax, with no evidence of malicious behavior.

1
Files scanned
276
Lines analyzed
2
Review items
3
False positives ignored

Confirmed security concerns (1)

Medium
Repository Command Execution Guidance
The skill instructs assistants to run grep, find, git log, and git show commands against the repository. This is appropriate for documentation verification, but it increases operational risk because commands inspect the local filesystem and git history.
The commands are explicitly documented and serve the stated documentation-sync workflow. I found no evidence that they exfiltrate data or execute untrusted generated shell strings.
Static false positives ignored (3)

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
Markdown Backtick Command Alerts Are False Positives
Several external-command alerts come from Markdown inline code or fenced examples, not Ruby-style backtick execution. These examples describe files and workflow steps rather than executable skill code.
The file is Markdown and the backticks delimit paths, examples, and report text. No executable Ruby code or shell backtick expansion exists in the skill file.
Low
Weak Cryptography Alerts Are False Positives
The weak-cryptography alerts match ordinary documentation words and headings, not cryptographic functions. No evidence found of MD5, SHA1, DES, or similar weak cryptographic operations.
The cited lines contain descriptive prose and an output template. They do not include cryptographic APIs, hashes, encryption calls, or security-sensitive transformations.
Low
Network Scanning Alert Is Vim Mapping Syntax
The network-scanning alert is caused by the string nmap inside a grep pattern for Vim mapping documentation. In this context, nmap means a Vim normal-mode mapping command, not a network scanner.
The line is a grep pattern that searches documentation for Vim mapping commands such as nmap, vmap, and map. It does not invoke the nmap network scanning tool.

Risk Factors

Detected Patterns

Shell and Git Commands in Skill Instructions
Audited by: codex

Jan 17, 2026, 06:37 AM

All 35 static findings are FALSE POSITIVES. The static analyzer misidentified markdown documentation text as security threats. SKILL.md is pure documentation containing workflow instructions and example bash commands shown as documentation - no executable code exists.

2
Files scanned
449
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jan 17, 2026, 06:37 AM

All 35 static findings are FALSE POSITIVES. The static analyzer misidentified markdown documentation text as security threats. SKILL.md is pure documentation containing workflow instructions and example bash commands shown as documentation - no executable code exists.

2
Files scanned
449
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jan 4, 2026, 04:30 PM

The skill contains only procedural guidance and documentation instructions. No executable code, file access, network operations, or system commands are present. It's purely a prompt-based workflow for documentation verification.

4
Files scanned
486
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 4, 2026, 04:30 PM

The skill contains only procedural guidance and documentation instructions. No executable code, file access, network operations, or system commands are present. It's purely a prompt-based workflow for documentation verification.

4
Files scanned
486
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude