Trust Assessment
claw-memory-guardian received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 8 findings: 3 critical, 0 high, 3 medium, and 2 low severity. Key findings include Arbitrary command execution, Unsafe deserialization / dynamic eval, Missing required field: name.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 33/100, 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 Findings8
| 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/betsymalthus/claw-memory-guardian/simple_test.js:9 | |
| 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/betsymalthus/claw-memory-guardian/test.js:10 | |
| CRITICAL | Unsanitized Configuration Value in Shell Script The `auto_save.sh` script, created by `index.js`, directly interpolates the `autoSaveInterval` value from `config.json` into a shell command (`sleep ${this.config.autoSaveInterval}`). If an attacker can modify `config.json` (which is typically user-controlled in the OpenClaw workspace), they can inject arbitrary shell commands by setting `autoSaveInterval` to a malicious string (e.g., '300; rm -rf /'). This leads to arbitrary command execution with the privileges of the skill. Sanitize or validate the `autoSaveInterval` configuration value before interpolating it into the shell script. Ensure it is a positive integer. A safer approach would be to pass the interval as an argument to the script and validate it within the script, or use a more robust method for scheduling tasks that doesn't involve direct shell interpolation of user-controlled values. | LLM | index.js:140 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/betsymalthus/claw-memory-guardian/simple_test.js:128 | |
| 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/betsymalthus/claw-memory-guardian/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency 'fs-extra' is not pinned to an exact version ('^11.2.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/betsymalthus/claw-memory-guardian/package.json | |
| 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/betsymalthus/claw-memory-guardian/package.json | |
| LOW | Unpinned or Loosely Pinned Dependencies The `package.json` file uses caret (`^`) ranges for dependencies (e.g., `"fs-extra": "^11.2.0"`). While common, this allows for automatic updates to minor and patch versions, which could potentially introduce vulnerabilities or breaking changes without explicit review. For higher security and stability, consider pinning exact versions or using tilde (`~`) ranges for patch updates only. Consider using exact version pinning (e.g., `"fs-extra": "11.2.0"`) or tilde ranges (e.g., `"fs-extra": "~11.2.0"`) for all dependencies. Regularly review and update dependencies to mitigate supply chain risks. | LLM | package.json:29 |
Scan History
Embed Code
[](https://skillshield.io/report/b264265193234dbf)
Powered by SkillShield