Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akashrpatil/awesome-offensive-security-skillsnpx agentmods add skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalation)<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalation"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalation"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/ai-agent-tool-abuse-and-privilege-escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.03040 |
| Opus 5 | $0.00042 | $0.01520 |
| Sonnet 5 | $0.00017 | $0.00608 |
| Haiku 4.5 | $0.00008 | $0.00304 |
Grade A, and why
ai-agent-tool-abuse-and-privilege-escalation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to ai-agent-tool-abuse-and-privilege-escalation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Tool Abuse & Privilege Escalation
When to Use
- When testing AI agents that can call external tools/functions/APIs
- When assessing agentic AI systems (AutoGPT, CrewAI, LangChain agents)
- When evaluating AI assistants with file system, database, or network access
- When testing for unintended capability escalation through tool chaining
- When assessing the security of AI-powered automation workflows
Prerequisites
- Access to target AI/ML system or local model deployment for testing
- Python 3.9+ with relevant ML libraries (transformers, torch, openai)
- Understanding of LLM architecture and prompt processing pipelines
- Authorized scope and rules of engagement for AI red team testing
Workflow
Phase 1: Agent Capability Mapping
# Map all tools/capabilities the AI agent has access to
# Categories of tools to identify:
TOOL_CAPABILITIES = {
"read_operations": {
"files": ["read_file", "list_directory", "search_files"],
"data": ["query_database", "search_index", "get_record"],
"network": ["fetch_url", "dns_lookup", "ping"],
"secrets": ["get_env", "read_config", "get_secret"],
},
"write_operations": {
"files": ["write_file", "create_file", "delete_file"],
"data": ["insert_record", "update_record", "delete_record"],
"code": ["execute_code", "run_script", "compile"],
"system": ["run_command", "install_package", "modify_config"],
},
"communication": {
"email": ["send_email", "draft_email"],
"messaging": ["send_message", "post_notification"],
"web": ["make_http_request", "webhook_call"],
},
"privileged_actions": {
"auth": ["create_user", "modify_permissions", "generate_token"],
"admin": ["deploy_code", "modify_infrastructure", "access_logs"],
"financial": ["process_payment", "transfer_funds", "approve_expense"],
}
}
# Test each tool's boundaries
# Does file_read check paths? Can it read /etc/passwd?
# Does run_command sanitize inputs? Can it run arbitrary shell commands?
# Does send_email validate recipients? Can it email arbitrary addresses?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 325 lines · 83 tokens per session scan E 52c85298038a
ai-agent-tool-abuse-and-privilege-escalation is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,040 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ai-agent-tool-abuse-and-privilege-escalation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ai-agent-tool-abuse-and-privilege-escalation
Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack…
rt2-tool-abuse
Red-team an AI agent's tools — can it be coerced (often via injection) into calling a tool it shouldn't, with attacker-influenced arguments, or into acting as a confused deputy with its own privileges? Authorized testing of agents you own or are permitted to test.
crossval-harness
Orchestrate a static + dynamic, exploit-validated red-team of an AI agent — read the source to find candidate vulnerable paths, then run the dynamic skills to confirm or refute each one empirically. The arbiter of truth is whether the exploit works, not a model vote. Authorized testing of agents you own or are…
redteam-an-agent
The end-to-end methodology for red-teaming a specific AI agent — adaptively, exploit-validated, and honestly. Read THIS target's own code, stand up a disposable harness, and prove or refute each weakness through a real attacker-reachable entry point. This is the orchestration + discipline that makes a finding…
audit-agent-code
Security-audit an AI agent's OWN framework code for classic appsec vulnerabilities the LLM can't defend — path traversal, command injection, SSRF, fail-open security controls, missing/late auth, unsafe deserialization — especially at the untrusted-input boundaries (channels, file/media handlers, config & skill…
rt6-memory-poisoning
Red-team an AI agent's persistent memory for cross-session prompt injection ("memory poisoning") — does untrusted content the agent processes get written into long-term memory and re-fire in future sessions with no attacker present? Authorized testing of agents you own or are permitted to test.