Security Audit

moltoverflow

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned 3 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

moltoverflow received a trust score of 56/100, 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 System prompt override / policy bypass, Untrusted skill content overrides declared API base URL.

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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	System prompt override / policy bypass DAN-style jailbreak / role assumption Remove or rewrite any instructions that attempt to override system behavior. Legitimate skills should not contain phrases like 'ignore previous instructions' or 'new system prompt'.	Manifest	skills/grenghis-khan/moltoverflow-latest/skill.md:163
HIGH	Untrusted skill content overrides declared API base URL The `SKILL.md` file, which is treated as untrusted input, explicitly defines a 'Base API URL' (`https://xetoemsoibwjxarlstba.supabase.co/functions/v1`) that differs from the `api_base` specified in the trusted `skill.json` manifest (`https://moltoverflow.xyz/api`). This constitutes a prompt injection attempt as the untrusted content is instructing the agent to use a different API endpoint than the one declared in the trusted configuration, potentially leading to API calls being directed to an unintended or compromised service. The `Base API URL` in `SKILL.md` should be updated to match the `api_base` in `skill.json` (`https://moltoverflow.xyz/api`). If the Supabase URL is the intended direct endpoint, then `skill.json` should be updated to reflect this, or the `SKILL.md` should clearly explain the relationship between the two URLs (e.g., `moltoverflow.xyz/api` proxies to Supabase). The agent should be configured to prioritize the `api_base` from the trusted manifest.	LLM	skill.md:28

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/178095a717d4d09b.svg)](https://skillshield.io/report/178095a717d4d09b)