📦

Audit History

portfolio-context - 5 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v5 LatestJul 20, 2026, 05:17 PM No confirmed findings0External commands
v4 Jun 27, 2026, 04:45 PM No confirmed findings0 External commands
v3 Jan 16, 2026, 12:14 PM No confirmed findings0No capability change
v2 Jan 16, 2026, 12:14 PM No confirmed findings0External commands
v1 Jan 10, 2026, 09:12 AM No confirmed findings0Baseline

Jul 20, 2026, 05:17 PM

All six static findings are false positives caused by Markdown inline and fenced code formatting. The skill contains project documentation only and no executable commands, network instructions, credential handling, or prompt-injection content.

1
Files scanned
99
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jun 27, 2026, 04:45 PM

Static analysis reported external command and weak cryptography patterns, but review found only Markdown inline code, a directory tree, and descriptive portfolio terminology. No executable code, shell invocation, cryptographic implementation, network access, filesystem access, secret handling, or prompt injection attempt was found in SKILL.md.

1
Files scanned
99
Lines analyzed
0
Review items
3
False positives ignored
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
False Positive: Markdown Inline Code Misread as Commands
The flagged text uses backticks to format TypeScript terms and repository paths in documentation. It is not Ruby or shell backtick execution, and no command is executed.
The evidence is plain Markdown prose and inline code formatting. There is no executable script context or interpolation target.
Low
False Positive: Code Fence Misread as Commands
The flagged code fence documents the project directory layout. It contains filenames only and does not define or invoke executable commands.
The lines are Markdown fence delimiters around a static directory listing. They do not contain command syntax or runtime behavior.
Low
False Positive: Weak Crypto Pattern in Documentation
The flagged lines describe portfolio analysis context and Sortino variance correction. No MD5, SHA-1, DES, RC4, or other weak cryptographic algorithm is used.
The lines are descriptive text about development context and statistical variance. I did not find evidence of cryptographic code or configuration.
No confirmed security findings were recorded for this completed audit.
Audited by: codex

Jan 16, 2026, 12:14 PM

This skill is a pure documentation/context file containing no executable code. All 22 static findings are FALSE POSITIVES caused by the analyzer misinterpreting JSON metadata fields, markdown code fences, and documentation text as security threats. No network calls, file access, or command execution capabilities exist.

2
Files scanned
277
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jan 16, 2026, 12:14 PM

This skill is a pure documentation/context file containing no executable code. All 22 static findings are FALSE POSITIVES caused by the analyzer misinterpreting JSON metadata fields, markdown code fences, and documentation text as security threats. No network calls, file access, or command execution capabilities exist.

2
Files scanned
277
Lines analyzed
1
Review items
0
False positives ignored
Audited by: claude

Jan 10, 2026, 09:12 AM

Pure markdown context file with no executable code. Contains project documentation only. No file access, network calls, or command execution capabilities. Safe for publication.

1
Files scanned
98
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude