Security Audit

bocha-search

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

bocha-search received a trust score of 77/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 4 findings: 0 critical, 0 high, 3 medium, and 1 low severity. Key findings include Unsafe deserialization / dynamic eval, Node lockfile missing, Unpinned dependency in publish script.

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

Manifest Analysis

86%

Static Code Analysis

100%

Dependency Graph

98%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

3 findings

Dynamic Code

2 findings

Security Findings4

Severity	Finding	Layer	Location
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/ypw757/bocha-skill/scripts/bocha_search.js:125
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/ypw757/bocha-skill/scripts/bocha_search.js:247
MEDIUM	Unpinned dependency in publish script The `publish.sh` script installs the `clawdhub` CLI globally without specifying a version. This introduces a supply chain risk, as a malicious update to the `clawdhub` package could be automatically installed and executed when the script is run. Pin the version of the `clawdhub` CLI to a known good version. For example, `npm install -g clawdhub@1.2.3` to ensure consistent and secure installations.	LLM	publish.sh:19
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/ypw757/bocha-skill/scripts/package.json

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5824d1aaa99b74d6.svg)](https://skillshield.io/report/5824d1aaa99b74d6)