Trust Assessment
resume-cv-builder received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via Keyword Extraction, Potential Command Injection and Excessive Permissions via Pandoc Arguments.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Keyword Extraction The skill demonstrates a shell command for keyword extraction that directly interpolates 'JOB_DESCRIPTION' into an `echo` command. If 'JOB_DESCRIPTION' is derived from untrusted user input without proper sanitization, an attacker could inject arbitrary shell commands (e.g., `JOB_DESCRIPTION="; rm -rf /; echo "`). This is a direct command injection vulnerability. Implement robust sanitization or escaping for any user-provided input before it is used in shell commands. Consider using a safer, programmatic method for text processing that avoids direct shell execution of untrusted strings. | LLM | SKILL.md:202 | |
| MEDIUM | Potential Command Injection and Excessive Permissions via Pandoc Arguments The skill explicitly requires and intends to use `pandoc` for file conversions, as indicated by `metadata.clawdbot.requires.bins` and example commands. While `pandoc` is a legitimate tool, if the skill allows user-controlled input for `pandoc` arguments (e.g., input/output filenames, custom CSS URLs, or metadata), it could lead to:
1. **Command Injection:** If a user can specify a malicious `--filter` or exploit a `pandoc` vulnerability via crafted input/arguments.
2. **Excessive Permissions:** If output file paths are user-controlled, it could allow writing to arbitrary locations on the filesystem. The `--css` argument also allows fetching external resources, which could be abused if the URL is untrusted. Strictly validate and sanitize all `pandoc` arguments derived from user input. Confine `pandoc` operations to a secure, temporary sandbox directory. Ensure that output file paths are not user-specifiable and that only allowed CSS URLs are used, or fetch and validate CSS content internally before passing it to `pandoc`. | LLM | SKILL.md:260 |
Scan History
Embed Code
[](https://skillshield.io/report/7e5c498c1d6b32ee)
Powered by SkillShield