Skill audit report
Adversarially review a specific change, design, or finding by having Claude debate one or more INDEPENDENT AI agents (e.g. Gemini or GPT in Antigravity, several models at once) over a shared file relay, with mandatory file:line citations, live read-only evidence, and a converge-or-two-positions outcome. Use when the user wants a different model's adversarial take before acting, mentions Antigravity / cross-agent / agent-exchange / "hash it out with Gemini", or wants a finding stress-tested by independent models. NOT for whole-project audits (that is committee-review) or quick single-pass checks. Needs at least one second agent the user drives and a shared directory both sides can read and write.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
FAIL30
23 GitHub stars
Stars/forks activity
FAIL32
23 stars, 3 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
8d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
FAIL38
command execution surface, credential or environment access
Install availability
PASS92
npx skills add randommonicle/claude-skills --skill cross-agent-review
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL18
secrets or environment access, shell or command execution
Repository evidence
PASS86
https://github.com/randommonicle/claude-skills/tree/main/cross-agent-review
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add randommonicle/claude-skills --skill cross-agent-review
Repository
88
https://github.com/randommonicle/claude-skills/tree/main/cross-agent-review
License
86
Apache-2.0
Maintenance
100
8d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
86
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options
Wazuh - The Open Source Security Platform. Unified XDR and SIEM protection for endpoints and cloud workloads.
16K Stars · Audit report
🕵️♂️ Collect a dossier on a person by username from 3000+ sites
33K Stars · Audit report
Nuclei is a fast, customizable vulnerability scanner powered by the global security community and built on a simple YAML-based DSL, enabling collaboration to tackle trending vulnerabilities on the internet. It helps you find vulnerabilities in your applications, APIs, networks, DNS, and cloud configurations.
29K Stars · Audit report
Usable description available
Dependency risk
38
command execution surface, credential or environment access
Install command safety
92
standard package or runtime install path
Permission surface
18
secrets or environment access, shell or command execution
Stars/forks activity
32
23 stars, 3 forks; issue activity unavailable in current metadata
Adoption
42
23 GitHub stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
Shell or command execution
highSkill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
Network access
mediumSkill likely fetches remote pages, APIs, repositories, or external services.
Filesystem access
mediumSkill may read or write project files, documents, generated artifacts, or local workspace state.
Secrets or environment access
highSkill metadata references credentials, tokens, environment variables, or secret-bearing workflows.