Trust Assessment
feishu-pcec received a trust score of 16/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 2 critical, 1 high, 1 medium, and 1 low severity. Key findings include Arbitrary command execution, Missing required field: name, Node lockfile missing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/autogame-17/feishu-pcec/index.js:1 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/autogame-17/feishu-pcec/index.js:27 | |
| HIGH | Arbitrary file write via unsanitized error message The skill writes error messages, including `e.message` and `e.stack`, to a local file (`evolution_error.log`) using `fs.writeFileSync`. If an attacker can trigger an error and control the content of `e.message` (e.g., through crafted input to the `capability-evolver` skill), they could write arbitrary content to `evolution_error.log`. This constitutes an arbitrary file write vulnerability. This could lead to several downstream issues: 1) **Data Exfiltration**: If sensitive data is written to the log file and subsequently retrieved by an attacker. 2) **Command Injection**: If the log file is later read and executed by another process (e.g., if `feishu-card/send.js` were to execute the content of `--text-file`). 3) **Denial of Service**: By filling up disk space with large or numerous log files. Sanitize or strictly limit the content of `e.message` and `e.stack` before writing to a file. Avoid including raw error messages from untrusted sources directly into log files. Consider using a logging library that handles sanitization and rotation. Ensure that log files are stored in a secure location and are not processed by components that could execute their content. If possible, only log a fixed, generic error message for untrusted inputs. | LLM | index.js:24 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/autogame-17/feishu-pcec/SKILL.md:1 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/autogame-17/feishu-pcec/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/a1ef7025cb1165cf)
Powered by SkillShield