Security Audit

lygo-universal-living-memory-library

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

lygo-universal-living-memory-library received a trust score of 72/100, 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: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, File system metadata leakage via broad default base path.

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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

86%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Security Findings3

Severity	Finding	Layer	Location
HIGH	File system metadata leakage via broad default base path The `audit_library.py` script's `--base` argument defaults to `Path(__file__).resolve().parents[3]`, which can resolve to a very broad directory like the file system root (`/`). The script then attempts to audit files specified in `core_files_index.json` relative to this base path. This allows the skill to probe for the existence, size, modification time, and SHA256 hash of files at arbitrary absolute paths (e.g., `/etc/passwd` if `core_files_index.json` contains `etc/passwd`, or `/home/user/.ssh/id_rsa` if `core_files_index.json` contains `home/user/.ssh/id_rsa`). The generated report, `living_memory_audit_report.json`, contains this metadata. An LLM could be prompted to invoke this skill and then read the report, leading to data exfiltration of sensitive file system metadata. Restrict the default value of the `--base` argument to a narrow, skill-specific sandbox directory. Implement strict validation for any user-provided `--base` argument to ensure it remains within an allowed, non-sensitive scope. Ensure `core_files_index.json` only contains paths relevant to the skill's intended operation and does not contain paths that could lead to sensitive system files when combined with a broad base.	LLM	scripts/audit_library.py:40
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/deepseekoracle/lygo-universal-living-memory-library/scripts/audit_library.py:8
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/deepseekoracle/lygo-universal-living-memory-library/scripts/self_check.py:6

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d22b85c12aa64c00.svg)](https://skillshield.io/report/d22b85c12aa64c00)