Skills debugger Audit History
๐Ÿ“ฆ

Audit History

debugger - 3 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v3 LatestJul 23, 2026, 12:57 PM 1 confirmed2No capability change
v2 Jul 22, 2026, 12:40 AM No confirmed findings0No capability change
v1 Jul 22, 2026, 12:40 AM No confirmed findings0Baseline

Jul 23, 2026, 12:57 PM

Two of 38 static findings are confirmed because the workflow runs project-controlled verification scripts that may execute arbitrary repository code. The remaining static findings are Markdown, safe examples, or explicit prohibitions. A separate medium-risk finding covers direct source edits and marker-based deletion.

1
Files scanned
225
Lines analyzed
4
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
Direct Source Mutation and Marker-Based Deletion
The workflow inserts logs directly into source files, then removes each marker and its following line. A misplaced marker could delete unintended code.
The instructions explicitly require direct log insertion and pair-based deletion. The source mutation is intentional, while the unintended-deletion risk depends on marker integrity.
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
Ruby/shell backtick execution
4. **ํšŒ๊ท€ ๊ฒŒ์ดํŠธ** โ†’ ํ”„๋กœ์ ํŠธ ๊ฒ€์ฆ ์Šคํฌ๋ฆฝํŠธ(`verify.sh`, `npm test`, `npm run build`, `pytest` ๋“ฑ)๊ฐ€ ์žˆ์œผ๋ฉด ์‹คํ–‰. ์žฌํ˜„ ์ฆ์ƒ์€ ์‚ฌ
The workflow explicitly runs verify.sh, package scripts, builds, or tests. Repository-controlled scripts can execute arbitrary code without a stated confirmation step.
Medium
Ruby/shell backtick execution
3. **ํšŒ๊ท€ ๊ฒŒ์ดํŠธ** โ†’ ํ”„๋กœ์ ํŠธ ๊ฒ€์ฆ ์Šคํฌ๋ฆฝํŠธ(`verify.sh`, `npm test`, `npm run build`, `pytest` ๋“ฑ)๊ฐ€ ์žˆ์œผ๋ฉด ์‹คํ–‰. ์‹œ๋‚˜๋ฆฌ์˜ค ์žฌํ˜„์€
The Playwright workflow explicitly runs project verification scripts and package commands. Those repository-controlled commands can execute arbitrary code without a stated confirmation step.
Audited by: codex

Jul 22, 2026, 12:40 AM

All 38 static findings are false positives. The scanner interpreted Markdown code spans and fences as shell backtick execution, while the environment-file reference explicitly prohibits logging to sensitive files. The skill is readable workflow documentation and contains no prompt injection, exfiltration instruction, or executable payload.

1
Files scanned
225
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jul 22, 2026, 12:40 AM

All 38 static findings are false positives. The scanner interpreted Markdown code spans and fences as shell backtick execution, while the environment-file reference explicitly prohibits logging to sensitive files. The skill is readable workflow documentation and contains no prompt injection, exfiltration instruction, or executable payload.

1
Files scanned
225
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude