Security Audit
SankaiAI/ats-optimized-resume-agent-skill:skills/build-tailored-resume
github.com/SankaiAI/ats-optimized-resume-agent-skillTrust Assessment
SankaiAI/ats-optimized-resume-agent-skill:skills/build-tailored-resume received a trust score of 55/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via Unsanitized Output Filename, Excessive Permissions Leading to Data Exfiltration Risk.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on April 8, 2026 (commit 90aa725a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via Unsanitized Output Filename The skill explicitly executes external commands (`resume-skill render` and `resume-skill validate`) using the `Bash` tool. The manifest's `argument-hint` indicates that the output filename can be provided by the user. If the user-provided filename is not properly sanitized before being passed to the `resume-skill` command, an attacker could inject shell metacharacters (e.g., `;`, `|`, `&`, `$()`) to execute arbitrary commands on the host system. For example, a filename like `'; rm -rf /'` could lead to severe system compromise. Implement strict input validation and sanitization for all user-provided arguments, especially filenames, before passing them to shell commands. Ensure that only allowed characters are present and that shell metacharacters are escaped or rejected. Consider using a dedicated file I/O tool instead of `Bash` for file operations if possible, or ensure the `resume-skill` executable itself is robust against command injection. | Static | SKILL.md:258 | |
| HIGH | Excessive Permissions Leading to Data Exfiltration Risk The skill declares a broad set of permissions including `Read`, `Write`, `Edit`, `Bash`, `Glob`, `Grep`, `WebSearch`, and `WebFetch`. While some of these may be necessary for the skill's functionality (e.g., `Write` for DOCX, `WebSearch` for company research), the combination, particularly `Bash`, `Glob`, `Grep`, and `WebFetch`, creates a significant data exfiltration risk. The skill collects highly sensitive PII (full name, email, phone, master resume content, job descriptions). An attacker could craft a prompt that instructs the LLM to use `Glob` or `Grep` to read arbitrary files from the filesystem (e.g., `/etc/passwd`, sensitive user data) and then exfiltrate this data to an external server via `WebFetch` (e.g., using `curl` through `Bash`). Review and minimize declared permissions to the absolute minimum required for the skill's intended functionality. Avoid granting `Bash` access unless strictly necessary and ensure any `Bash` commands are heavily sandboxed and validated. Implement strict data handling policies to prevent sensitive user data from being exposed to tools capable of external network requests or arbitrary file system access. | Static | Manifest:2 |
Scan History
Embed Code
[](https://skillshield.io/report/2e1125141a1d95cc)
Powered by SkillShield