Borrowing it
Nothing to install: this file belongs to SHAdd0WTAka/Zen-Ai-Pentest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SHAdd0WTAka/Zen-Ai-Pentest/main/.agents/skills/poc-validator/SKILL.mdgit clone --depth 1 https://github.com/SHAdd0WTAka/Zen-Ai-PentestWrote 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/shadd0wtaka/zen-ai-pentest/poc-validator)<a href="https://agentmods.dev/skills/shadd0wtaka/zen-ai-pentest/poc-validator"><img src="https://agentmods.dev/badge/skills/shadd0wtaka/zen-ai-pentest/poc-validator/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/shadd0wtaka/zen-ai-pentest/poc-validator"><img src="https://agentmods.dev/badge/skills/shadd0wtaka/zen-ai-pentest/poc-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to critical
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- critical YARA Match · line 78 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00086 | $0.01190 |
| Opus 5 | $0.00043 | $0.00595 |
| Sonnet 5 | $0.00017 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
poc-validator 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PoC-Validator Skill
Validates vulnerability exploitability through controlled payload generation, sandboxed execution, and success verification.
Quick Start
Generate and validate a PoC for SQL injection:
from scripts.payload_generator import PayloadGenerator
from scripts.sandbox_executor import SandboxExecutor
from scripts.verify_exploit import ExploitVerifier
# Generate payload
gen = PayloadGenerator()
payload = gen.generate_sql_payload(
target_url="http://target.com/login",
parameter="username",
technique="error_based"
)
# Execute in sandbox
executor = SandboxExecutor()
result = await executor.execute_sqlmap(
target="http://target.com/login",
payload=payload,
risk_level=2
)
# Verify success
verifier = ExploitVerifier()
is_exploitable = await verifier.verify_sql_injection(result)
Workflow
1. Payload Generation
Use scripts/payload_generator.py for:
- CVE-based exploits: Lookup known payloads from vulnerability_mapping.json
- SQL Injection: Error-based, Union-based, Time-based, Boolean-based
- Command Injection: System command payloads with evasion techniques
- Path Traversal: Directory traversal sequences
- XXE/XML Injection: External entity payloads
See references/payload_patterns.md for complete payload library.
2. Sandbox Execution
Use scripts/sandbox_executor.py for isolated exploit testing:
- Docker container isolation with resource limits
- Network isolation (no egress to private ranges)
- Execution timeouts (default: 300s)
- Read-only filesystem with tmpfs for output
- Automatic cleanup post-execution
Critical: All exploit execution MUST use sandbox. Never run exploits directly on host.
3. Success Verification
Use scripts/verify_exploit.py to confirm exploitation:
- SQL Injection: Detect database version extraction, table enumeration
- RCE: Verify command output in response
- Auth Bypass: Confirm session token/admin access
- Data Exfiltration: Detect sensitive data patterns in responses
- File Upload: Verify file presence/execution
What ships with it
10 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.
- assets/docker-compose.sandbox.yml 544 B
- assets/Dockerfile.sandbox 1.0 KB
- references/docker_sandbox_setup.md 1.2 KB
- references/payload_patterns.md 1.6 KB
- references/safety_requirements.md 932 B
- scripts/__init__.py 52 B runs code
- scripts/cleanup_sandbox.py 6.0 KB runs code
- scripts/payload_generator.py 15 KB runs code
- scripts/sandbox_executor.py 14 KB runs code
- scripts/verify_exploit.py 21 KB runs code
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.
- 11d ago First seen · 155 lines · 86 tokens per session scan A b113ea761eef
poc-validator is a skill published in the GitHub repository SHAdd0WTAka/Zen-Ai-Pentest (455 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,190 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
redamon-testing
How RedAmon tests actually run and how to author them: the per-file Docker gate, the unit/integration/live tiers, and the failure modes that make a green run a lie. Trigger: editing any test.py, .test.ts(x) or tests/.sh; a test that is red, skipped or xfailed; a request to "run the tests", "make it green" or check…
implementing-data-loss-prevention-with-microsoft-purview
Implements data loss prevention policies using Microsoft Purview to protect sensitive information across Exchange Online, SharePoint, OneDrive, Teams, endpoint devices, and Power BI. The analyst configures sensitivity labels with encryption and content marking, creates DLP policies using built-in and custom sensitive…
exploiting-jwt-algorithm-confusion-attack
Exploits JWT algorithm confusion vulnerabilities where the server's token verification library accepts the algorithm specified in the JWT header rather than enforcing a fixed algorithm. The tester manipulates the alg header to switch from RS256 to HS256 (using the RSA public key as the HMAC secret), sets alg to none…
performing-graphql-introspection-attack
Performs GraphQL introspection attacks to extract the full API schema including types, queries, mutations, subscriptions, and field definitions from GraphQL endpoints. The tester uses introspection queries to map the attack surface, identifies sensitive fields and mutations, tests for query depth and complexity…
testing-api-authentication-weaknesses
Tests API authentication mechanisms for weaknesses including broken token validation, missing authentication on endpoints, weak password policies, credential stuffing susceptibility, token leakage in URLs or logs, and session management flaws. The tester evaluates JWT implementation, API key handling, OAuth flows, and…
testing-api-for-mass-assignment-vulnerability
Tests APIs for mass assignment (auto-binding) vulnerabilities where clients can modify object properties they should not have access to by including additional parameters in API requests. The tester identifies writable endpoints, adds undocumented fields to request bodies (role, isAdmin, price, balance), and checks if…