📦

Audit History

shellcheck-configuration - 8 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v8 LatestJul 8, 2026, 02:03 PM No confirmed findings0No capability change
v7 Jul 8, 2026, 02:03 PM No confirmed findings0No capability change
v6 Jul 1, 2026, 01:10 AM No confirmed findings4No capability change
v5 Jul 1, 2026, 01:10 AM No confirmed findings4No capability change
v4 Jan 17, 2026, 10:09 AM No confirmed findings0No capability change
v3 Jan 17, 2026, 10:09 AM No confirmed findings0Network accessExternal commandsFilesystem access
v2 Jan 4, 2026, 04:24 PM No confirmed findings0No capability change
v1 Jan 4, 2026, 04:24 PM No confirmed findings0Baseline

Jul 8, 2026, 02:03 PM

Static analysis flagged many command, filesystem, and network patterns, but all reviewed instances are documentation examples in SKILL.md. No executable skill code, prompt injection attempt, data exfiltration intent, or hidden persistence behavior was found.

1
Files scanned
455
Lines analyzed
3
Review items
0
False positives ignored
Audited by: codex

Jul 8, 2026, 02:03 PM

Static analysis flagged many command, filesystem, and network patterns, but all reviewed instances are documentation examples in SKILL.md. No executable skill code, prompt injection attempt, data exfiltration intent, or hidden persistence behavior was found.

1
Files scanned
455
Lines analyzed
3
Review items
0
False positives ignored
Audited by: codex

Jul 1, 2026, 01:10 AM

Static analysis reported many command, filesystem, network, and blocker patterns, but review shows they are documentation examples for ShellCheck usage. No prompt injection, credential access, data exfiltration, persistence, or malicious execution intent was found in SKILL.md.

1
Files scanned
455
Lines analyzed
7
Review items
0
False positives ignored
Capability review items (4)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low
Shell Command Examples Are Documentation
The external command detections occur in fenced examples showing how to install ShellCheck, run it locally, add CI checks, and parallelize linting. These commands are relevant to the skill purpose and do not show hidden execution, user-input command injection, or unauthorized behavior.
The matched lines are visibly fenced examples and workflow snippets for ShellCheck. The semantic context supports legitimate documentation rather than executable malware.
Low
Configuration File References Are Expected
The hidden file matches reference .shellcheckrc and shell profile paths as configuration examples. They do not instruct the model to read secrets, modify unrelated user files, or persist unauthorized changes.
The file paths are standard examples for ShellCheck and shell configuration guidance. No sensitive file harvesting or broad filesystem traversal was found.
Low
Network URLs Point To Public ShellCheck Resources
The hardcoded URLs identify the official ShellCheck repository, wiki, and reference site. They are informational links and do not transmit local data or credentials.
The URLs are public ShellCheck resources used for installation and documentation. No outbound request code or exfiltration target appears in the file.
Low
Blocker Keywords Are ShellCheck Terminology
The blocker keyword matches come from ShellCheck rule names, disable directives, source annotations, process examples, and command comments. They are not command-and-control instructions or prompt-injection attempts.
The suspicious terms are embedded in normal ShellCheck examples and rule explanations. I found no text instructing the evaluator or assistant to override security rules.

Detected Patterns

Privilege Escalation Command In CI ExampleExternal Source Checkout ExampleParallel Command Execution Example
Audited by: codex

Jul 1, 2026, 01:10 AM

Static analysis reported many command, filesystem, network, and blocker patterns, but review shows they are documentation examples for ShellCheck usage. No prompt injection, credential access, data exfiltration, persistence, or malicious execution intent was found in SKILL.md.

1
Files scanned
455
Lines analyzed
7
Review items
0
False positives ignored
Capability review items (4)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low
Shell Command Examples Are Documentation
The external command detections occur in fenced examples showing how to install ShellCheck, run it locally, add CI checks, and parallelize linting. These commands are relevant to the skill purpose and do not show hidden execution, user-input command injection, or unauthorized behavior.
The matched lines are visibly fenced examples and workflow snippets for ShellCheck. The semantic context supports legitimate documentation rather than executable malware.
Low
Configuration File References Are Expected
The hidden file matches reference .shellcheckrc and shell profile paths as configuration examples. They do not instruct the model to read secrets, modify unrelated user files, or persist unauthorized changes.
The file paths are standard examples for ShellCheck and shell configuration guidance. No sensitive file harvesting or broad filesystem traversal was found.
Low
Network URLs Point To Public ShellCheck Resources
The hardcoded URLs identify the official ShellCheck repository, wiki, and reference site. They are informational links and do not transmit local data or credentials.
The URLs are public ShellCheck resources used for installation and documentation. No outbound request code or exfiltration target appears in the file.
Low
Blocker Keywords Are ShellCheck Terminology
The blocker keyword matches come from ShellCheck rule names, disable directives, source annotations, process examples, and command comments. They are not command-and-control instructions or prompt-injection attempts.
The suspicious terms are embedded in normal ShellCheck examples and rule explanations. I found no text instructing the evaluator or assistant to override security rules.

Detected Patterns

Privilege Escalation Command In CI ExampleExternal Source Checkout ExampleParallel Command Execution Example
Audited by: codex

Jan 17, 2026, 10:09 AM

Pure documentation skill containing only markdown guidance for ShellCheck, a legitimate open-source static analysis tool. All static findings are false positives. References like SC2009, SC2086 are ShellCheck error codes (not C2 keywords), sha256sum is appropriate for caching (not weak crypto), and shell examples are documentation (not malicious patterns).

2
Files scanned
631
Lines analyzed
3
Review items
0
False positives ignored
Audited by: claude

Jan 17, 2026, 10:09 AM

Pure documentation skill containing only markdown guidance for ShellCheck, a legitimate open-source static analysis tool. All static findings are false positives. References like SC2009, SC2086 are ShellCheck error codes (not C2 keywords), sha256sum is appropriate for caching (not weak crypto), and shell examples are documentation (not malicious patterns).

2
Files scanned
631
Lines analyzed
3
Review items
0
False positives ignored
Audited by: claude

Jan 4, 2026, 04:24 PM

Pure documentation skill containing only markdown guidance and JSON configuration. No executable code, no file access, no network calls. Safe for publication.

4
Files scanned
800
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, 04:24 PM

Pure documentation skill containing only markdown guidance and JSON configuration. No executable code, no file access, no network calls. Safe for publication.

4
Files scanned
800
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude