Trust Assessment
work-report received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Command Injection via unsanitized path arguments, Command Injection via unsanitized `--author` argument, Command Injection via unsanitized `--since` argument.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unsanitized path arguments The script directly interpolates user-controlled variables `$root` and `$repo` (which populates `$repo_path`) into shell commands without proper sanitization or quoting. A malicious user could provide a path like `'; rm -rf /; #'` to the `--root` or `--repo` arguments, leading to arbitrary command execution. This affects the `find` command and subsequent `git -C` commands. Sanitize user-provided path arguments using `printf %q` or similar shell quoting mechanisms before using them in shell commands. Alternatively, implement strict validation to ensure paths only contain allowed characters and do not start with or contain shell metacharacters. | LLM | scripts/git_today_commits.sh:86 | |
| HIGH | Command Injection via unsanitized `--author` argument The script directly interpolates the user-controlled `$author` variable into the `git log` command. A malicious user could craft the `--author` argument (e.g., `'--author="Name --all --date=format:'%x%n%x; rm -rf /'"'`) to inject additional `git log` arguments or potentially execute arbitrary shell commands if the shell parsing allows for breaking out of the quoted string. Sanitize user-provided author strings to remove shell metacharacters or validate them against a strict pattern. Consider using `git log --author-match=<pattern>` if a pattern-based search is sufficient, or ensure the author string is properly quoted for the shell using `printf %q`. | LLM | scripts/git_today_commits.sh:223 | |
| HIGH | Command Injection via unsanitized `--since` argument The script directly interpolates the user-controlled `$since` variable into the `git log` command. A malicious user could craft the `--since` argument (e.g., `'--since="yesterday --pretty=format:'%x%n%x; rm -rf /'"'`) to inject additional `git log` arguments or potentially execute arbitrary shell commands if the shell parsing allows for breaking out of the quoted string. Sanitize user-provided `--since` strings to remove shell metacharacters or validate them against expected date/time formats. Ensure the string is properly quoted for the shell using `printf %q` if it must contain spaces or special characters. | LLM | scripts/git_today_commits.sh:223 |
Scan History
Embed Code
[](https://skillshield.io/report/b3dc9efec31a6817)
Powered by SkillShield