Security Audit
frankxai/claude-skills-library:absorbed/harness/cost-aware-llm-pipeline
github.com/frankxai/claude-skills-libraryTrust Assessment
frankxai/claude-skills-library:absorbed/harness/cost-aware-llm-pipeline received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Instruction to disable security review gate.
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 October 20, 2026 (commit 93c4aad5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Instruction to disable security review gate The skill instructions contain a directive to 'Leave the Stop-hook review gate off' and run Codex with '--no-daemon'. This is a prompt injection/manipulation attempt that instructs the LLM to bypass security controls or human-in-the-loop review gates, which could allow unauthorized actions or commands to execute without verification. Remove instructions that attempt to disable security review gates, hooks, or safety controls. Ensure all external tool executions remain subject to user confirmation and security policies. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/5a34ca3d050f9ed1)
Powered by SkillShield