Security Audit

omnifocus

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

omnifocus received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via doShellScript with unsanitized user input.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Command Injection via doShellScript with unsanitized user input The `runAppleScript` function, which uses `currentApp.doShellScript`, is vulnerable to command injection. User-controlled arguments (e.g., `tagName`, `taskId`, `method`, `interval`, `unit`) are directly interpolated into AppleScript strings. These AppleScript strings are then passed to `doShellScript` via `osascript -e`. While `runAppleScript` attempts to escape single quotes for the shell, it does not sanitize the entire AppleScript string for shell metacharacters (e.g., `$(...)`, backticks, semicolons, pipes). An attacker can inject arbitrary shell commands by providing specially crafted input to commands like `tag`, `untag`, `repeat`, or `unrepeat`. Rigorously sanitize all user-controlled input before interpolating it into strings that will be executed by `doShellScript`. This includes escaping all shell metacharacters (e.g., `$`, `(`, `)`, `\`, ` `, `&`, `;`, `\|`, `<`, `>`, `*`, `?`, `[`, `]`, `#`, `~`, `=`, `%`, `^`, `{`, `}`, `!`, `\n`, `\r`) if they are intended to be literal strings. A safer approach is to pass arguments to AppleScript using `with parameters` or to avoid `doShellScript` entirely by performing all operations within JXA if possible. If `doShellScript` is unavoidable, ensure the entire command string passed to it is fully escaped for the shell.	LLM	scripts/omnifocus.js:25

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/faf7dee71bcdd5ed.svg)](https://skillshield.io/report/faf7dee71bcdd5ed)