Skills security Audit History
📦

Audit History

security - 8 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v8 LatestJul 6, 2026, 05:14 AM No confirmed findings0No capability change
v7 Jul 6, 2026, 05:14 AM No confirmed findings0No capability change
v6 Jun 28, 2026, 06:14 PM 1 confirmed0No capability change
v5 Jan 16, 2026, 08:48 PM No confirmed findings0No capability change
v4 Jan 16, 2026, 08:48 PM No confirmed findings0External commands
v3 Jan 10, 2026, 11:40 AM No confirmed findings0No capability change
v2 Jan 10, 2026, 11:40 AM No confirmed findings0No capability change
v1 Jan 10, 2026, 11:40 AM No confirmed findings0Baseline

Jul 6, 2026, 05:14 AM

The only static finding is a Markdown bash code block listing hardcoded security commands. I found no executable code, prompt injection, credential exfiltration, or malicious intent in SKILL.md.

1
Files scanned
72
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: codex

Jul 6, 2026, 05:14 AM

The only static finding is a Markdown bash code block listing hardcoded security commands. I found no executable code, prompt injection, credential exfiltration, or malicious intent in SKILL.md.

1
Files scanned
72
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: codex

Jun 28, 2026, 06:14 PM

Static analysis flagged a command block and two weak-cryptography patterns. The command block is documented guidance for local security tools, while the weak-cryptography matches are false positives in descriptive security text.

1
Files scanned
72
Lines analyzed
2
Review items
1
False positives ignored

Confirmed security concerns (1)

Low
Documented External Security Commands
The skill lists local commands for GPG, SSH, git signing, Bandit, pip-audit, Safety, and Semgrep. These are not auto-executed by the skill, but users should review commands before running them in a project.
The command block is present and clearly invokes external tools. Confidence is high that the pattern exists, but the security impact is low because SKILL.md only documents commands.
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
Weak Cryptography Static Matches Are False Positives
The static weak-cryptography findings point to general security prose and an OWASP item about insecure deserialization. No weak cryptographic algorithm or implementation guidance is present at these locations.
The cited lines contain descriptive text, not cryptographic code or algorithm recommendations. There is no evidence of MD5, SHA1, DES, RC4, or similar weak crypto usage.

Risk Factors

⚙️ External commands (1)

Detected Patterns

External Command Guidance
Audited by: codex

Jan 16, 2026, 08:48 PM

This is a documentation-only skill containing no executable code. Both SKILL.mdare metadata and documentation files that describe security workflows and list example bash commands as documentation. No file system access, network calls, or code execution capabilities exist. All 12 static findings are FALSE POSITIVES caused by the scanner misidentifying documentation keywords as security vulnerabilities.

2
Files scanned
250
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: claude

Jan 16, 2026, 08:48 PM

This is a documentation-only skill containing no executable code. Both SKILL.mdare metadata and documentation files that describe security workflows and list example bash commands as documentation. No file system access, network calls, or code execution capabilities exist. All 12 static findings are FALSE POSITIVES caused by the scanner misidentifying documentation keywords as security vulnerabilities.

2
Files scanned
250
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: claude

Jan 10, 2026, 11:40 AM

This is a documentation-only skill containing no executable code. The SKILL.md file describes security workflows and lists command examples as documentation. It references standard security tools (GPG, SSH, Bandit, pip-audit, Safety, Semgrep) that users run directly. No file system access, network calls, or code execution capabilities are present.

1
Files scanned
67
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, 11:40 AM

This is a documentation-only skill containing no executable code. The SKILL.md file describes security workflows and lists command examples as documentation. It references standard security tools (GPG, SSH, Bandit, pip-audit, Safety, Semgrep) that users run directly. No file system access, network calls, or code execution capabilities are present.

1
Files scanned
67
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, 11:40 AM

This is a documentation-only skill containing no executable code. The SKILL.md file describes security workflows and lists command examples as documentation. It references standard security tools (GPG, SSH, Bandit, pip-audit, Safety, Semgrep) that users run directly. No file system access, network calls, or code execution capabilities are present.

1
Files scanned
67
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude