Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/xamirhamza77/reverseops-skill/exploit-validationnpx skills add xAmirHamza77/ReverseOps-Skill --skill exploit-validationgit clone --depth 1 https://github.com/xAmirHamza77/ReverseOps-SkillWhat 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 | $0.00083 | $0.00957 |
| Opus 5 | $0.00042 | $0.00478 |
| Sonnet 5 | $0.00017 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
exploit-validation 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACTION REQUIRED (execute immediately after reading)
NOW: scope.mdauth.status=granted+ the target is in the in-scope asset list; if not, stop and go back toosint-recon/or case-initNOW: classify the destructive level of this validation (read-only / write test data / may impact service); anything beyond the level authorized in scope must be escalatedNEXT: build the hypothesis matrix; one row per candidateACT: minimal repro + negative control → verdict written to Evidence; confirmed findings get a JSON finding (../reporting/finding-schema.json), then runscripts/mkreport.pyACT: after a fix ships, retest; status movesconfirmed → fixed / accepted
exploit-validation — from "candidate" to "confirmed"
Validation state machine
candidate ─→ confirmed (repro + control + impact statement)
│ ─→ false-positive (control experiment disproves it)
└─────→ unverifiable (environment/permission limits — record the gap,
keep it out of the report main table)
A scanner hit is not a vulnerability. The entire value of this skill is turning the dial from "looks like" to "can prove".
Hypothesis matrix (write before touching the target)
| # | Candidate | Source | Falsifiable hypothesis | Minimal repro idea | Expected control |
|---|---|---|---|---|---|
| 1 | /api/login rate-limit bypass | scan + 429 observation | XFF is used as the throttle key | same request, N times with/without XFF | no XFF = 429; forged XFF = 200 |
| 2 | ... |
Every hypothesis must be falsifiable — if you can't write a control experiment, go back to information gathering.
Minimal-repro discipline
- Minimal: if one request or one command demonstrates it, never use a chain; strip every header/parameter unrelated to the bug from the PoC
- Control: every PoC ships with a "must not succeed" request (no XFF / no metachars / no foreign ID). Both sides together make evidence
- Idempotence-aware: prefer GET/HEAD probes; for write operations use a test account + self-cleanup (create then delete), and log it in the timeline
- Rate guardrails: default ≤ 30 req/min on production; brute-force/enumeration thresholds get their own line in scope.md
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.
- 2d ago First seen · 82 lines · 83 tokens per session scan A 2e30d00ae4e0
exploit-validation is a skill published in the GitHub repository xAmirHamza77/ReverseOps-Skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 957 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 2026-08-31.
Other skills, from other repositories
managed-pentesting-with-strix
Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed. Create an API token, register domain/repository assets, launch and poll scans, triage vulnerabilities, export SARIF, download PDF/DOCX pentest reports for SOC 2 and other compliance evidence…
fix-security-vulnerabilities-with-strix
Fix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by severity, patch the root cause rather than the symptom, and re-run Strix to prove each fix actually closes the exploit. Handles injection, XSS, SSRF, broken access control, IDOR, and other validated findings. Use…
find-security-vulnerabilities-in-code
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy…
analyzing-malware-behavior-with-cuckoo-sandbox
Detonate malware samples in Cuckoo Sandbox to observe runtime behavior — process creation, file system and registry changes, network communications, and API calls — and generate behavioral reports for classification and IOC extraction. Use when a sample has passed static triage and needs dynamic/behavioral analysis…
analyzing-network-traffic-for-incidents
Analyzes network traffic captures and flow data to identify adversary activity during security incidents, including command-and-control communications, lateral movement, data exfiltration, and exploitation attempts. Uses Wireshark, Zeek, and NetFlow analysis techniques. Activates for requests involving network traffic…
analyzing-network-traffic-of-malware
Analyzes network traffic generated by malware during sandbox execution or live incident response to identify C2 protocols, data exfiltration channels, payload downloads, and lateral movement patterns using Wireshark, Zeek, and Suricata. Activates for requests involving malware network analysis, C2 traffic decoding…