Audit History
file-search - 7 audits
Version comparison
Capability and finding changes across audited versions, newest first.
| Version | Date | Result | Review items | Change vs previous |
|---|---|---|---|---|
| v7 Latest | 4 juil. 2026, 12:56 | 1 confirmed | 4 | No capability change |
| v6 | 4 juil. 2026, 12:56 | 1 confirmed | 4 | No capability change |
| v5 | 4 juil. 2026, 16:27 | 1 confirmed | 4 | Contains scripts Filesystem access |
| v4 | 27 juin 2026, 11:31 | No confirmed findings | 2 | Filesystem access Contains scripts |
| v3 | 16 janv. 2026, 13:34 | No confirmed findings | 0 | No capability change |
| v2 | 16 janv. 2026, 13:34 | No confirmed findings | 0 | Contains scriptsExternal commands |
| v1 | 10 janv. 2026, 08:47 | No confirmed findings | 0 | Baseline |
4 juil. 2026, 12:56
Most static findings are markdown examples or safe command documentation, including false positives from fenced code blocks. Confirmed risks are limited to destructive or broad file-changing shell workflows, and no prompt injection or data exfiltration evidence was found.
Confirmed security concerns (1)
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.
Risk Factors
⚡ Contains scripts (1)
⚙️ External commands (40)
4 juil. 2026, 12:56
Most static findings are markdown examples or safe command documentation, including false positives from fenced code blocks. Confirmed risks are limited to destructive or broad file-changing shell workflows, and no prompt injection or data exfiltration evidence was found.
Confirmed security concerns (1)
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.
Risk Factors
⚡ Contains scripts (1)
⚙️ External commands (40)
4 juil. 2026, 16:27
The skill is documentation for local fd, ripgrep, and fzf workflows, with no prompt injection text or network behavior found. Most Markdown backtick detections are false positives, but several advanced examples perform bulk replacement or destructive file deletion. Users should treat advanced commands as manual examples and review selections before execution.
Confirmed security concerns (1)
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.
Risk Factors
⚡ Contains scripts (1)
⚙️ External commands (40)
27 juin 2026, 11:31
Static analysis flagged many command patterns because this skill is Bash-focused documentation for fd, ripgrep, and fzf. The weak-crypto and dynamic-import alerts are false positives, but the skill does include legitimate examples that can modify or delete files when executed. No evidence found for malware, credential access, network exfiltration, obfuscation, or prompt injection.
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.
Static false positives ignored (2)
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.
Risk Factors
⚙️ External commands (5)
Detected Patterns
16 janv. 2026, 13:34
Pure documentation skill containing only markdown files. No executable code, no MCP definitions, no network calls, no file system access, and no command execution. The skill provides informational content about using fd, ripgrep, and fzf command-line tools. All static findings are FALSE POSITIVES - the scanner misinterpreted markdown code block examples as executable commands.
Risk Factors
⚡ Contains scripts (1)
⚙️ External commands (85)
16 janv. 2026, 13:34
Pure documentation skill containing only markdown files. No executable code, no MCP definitions, no network calls, no file system access, and no command execution. The skill provides informational content about using fd, ripgrep, and fzf command-line tools. All static findings are FALSE POSITIVES - the scanner misinterpreted markdown code block examples as executable commands.
Risk Factors
⚡ Contains scripts (1)
⚙️ External commands (85)
10 janv. 2026, 08:47
Pure documentation skill containing only markdown files. No executable code, no MCP definitions, no network calls, no file system access, and no command execution. The skill provides informational content about using fd, ripgrep, and fzf command-line tools.