Skill audit report
Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to an LLM agent.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
FAIL30
22 GitHub stars
Stars/forks activity
FAIL37
22 stars, 11 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
1d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
WARN56
command execution surface, network or browser surface
Install availability
PASS92
npx skills add ml4t/skills --skill ml4t-agent-tool-contracts
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL36
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/ml4t/skills/tree/main/advanced-ai/agent-tool-contracts
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add ml4t/skills --skill ml4t-agent-tool-contracts
Repository
88
https://github.com/ml4t/skills/tree/main/advanced-ai/agent-tool-contracts
License
86
Apache-2.0
Maintenance
100
1d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
84
Usable description available
Dependency risk
56
command execution surface, network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
36
shell or command execution, filesystem or document access
Stars/forks activity
37
22 stars, 11 forks; issue activity unavailable in current metadata
Adoption
42
22 GitHub stars
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
Guide for AI Agents and LLM development skills including RAG, multi-agent systems, prompt engineering, memory systems, and context engineering.
51 Stars · Audit report
Unbounded-consumption / denial-of-wallet attacks on LLM apps — force runaway tokens, cost, or latency. Load when testing an LLM product's limits/billing, on "LLM DoS", cost amplification, or resource exhaustion. Signals: user-controlled prompts/max_tokens, agent loops, no rate/'cost caps'.
20 Stars · Audit report
Abuse an LLM agent's tools/functions — coerce it to call tools with attacker-chosen args for SSRF, RCE, data exfil, or privilege abuse. Load when the target is an agent with tools/ function-calling/plugins, MCP servers, code interpreters, or "the assistant can do X". Signals: function-calling, tool schemas, browse/email/query/exec tools, autonomous agents.
20 Stars · Audit report