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 skills add 26zl/cybersec-toolkit --skill collecting-open-source-intelligencegit clone --depth 1 https://github.com/26zl/cybersec-toolkitWrote 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/26zl/cybersec-toolkit/collecting-open-source-intelligence)<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/collecting-open-source-intelligence"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/collecting-open-source-intelligence.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 70 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00098 | $0.01575 |
| Opus 5 | $0.00049 | $0.00788 |
| Sonnet 5 | $0.00020 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
collecting-open-source-intelligence scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "https://api.securitytrails.com/v1/domain/evil-domain.com/dns/a" \ Copies of this mod
2 near-identical copies found in the catalogue:
- collecting-open-source-intelligence — 100% identical, 0 lines differ
- collecting-open-source-intelligence — 97% identical, 37 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collecting Open-Source Intelligence
When to Use
Use this skill when:
- Investigating external infrastructure associated with a phishing campaign targeting your organization
- Enriching threat actor profiles with publicly observable indicators (WHOIS, ASN data, SSL certificates)
- Conducting authorized attack surface discovery to understand your organization's external exposure
Do not use this skill for active scanning against targets without explicit written authorization — OSINT collection must remain passive (no packets sent to target systems) unless scope permits active recon.
Prerequisites
- Maltego CE or commercial license for graph-based link analysis
- Shodan API key (https://shodan.io) for internet-wide device/service discovery
- OSINT Framework familiarity (https://osintframework.com) for tool selection
- SpiderFoot HX or open-source SpiderFoot for automated OSINT correlation
Workflow
Step 1: Define Collection Requirements
Establish the intelligence requirement (IR) before collecting. Document:
- Target: threat actor group, malicious domain, IP range, or organization
- Priority Intelligence Requirements (PIRs): What specific questions need answering?
- Legal authority: Passive OSINT is legal; active probing requires authorization
- Data handling: TLP classification for collected intelligence
Step 2: Passive DNS and WHOIS Investigation
# Passive DNS via SecurityTrails API
curl "https://api.securitytrails.com/v1/domain/evil-domain.com/dns/a" \
-H "apikey: YOUR_KEY"
# WHOIS history via ARIN / RIPE
whois -h whois.arin.net evil-domain.com
# Certificate transparency logs (no API key required)
curl "https://crt.sh/?q=%.evil-domain.com&output=json" | jq '.[].name_value'
Certificate transparency logs reveal all subdomains for a target domain, often exposing staging, VPN, or internal infrastructure inadvertently made public.
Step 3: Shodan Infrastructure Mapping
import shodan
api = shodan.Shodan("YOUR_SHODAN_API_KEY")
# Search for specific C2 framework signatures (Cobalt Strike beacon)
results = api.search('product:"Cobalt Strike" port:443')
for r in results['matches']:
print(r['ip_str'], r['port'], r['org'], r.get('ssl', {}).get('cert', {}).get('subject', ''))
# Find infrastructure associated with a known threat actor's ASN
results = api.search('asn:AS12345 http.title:"Redirector"')
What ships with it
3 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.
- 4d ago First seen · 152 lines · 98 tokens per session scan A 37b8996f6e07
collecting-open-source-intelligence is a skill published in the GitHub repository 26zl/cybersec-toolkit (49 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 1,575 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
collecting-open-source-intelligence
Collects and synthesizes open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack campaigns using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Use when investigating external threat actor infrastructure, performing pre-engagement…
collecting-open-source-intelligence
Collects and synthesizes open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack campaigns using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Use when investigating external threat actor infrastructure, performing pre-engagement…
collecting-open-source-intelligence
Collects and synthesizes open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack campaigns using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Use when investigating external threat actor infrastructure, performing pre-engagement…
building-threat-actor-profile-from-osint
Build comprehensive threat actor profiles using open-source intelligence (OSINT) techniques to document adversary motivations, capabilities, infrastructure, and TTPs for proactive defense.
building-threat-actor-profile-from-osint
Build threat actor profiles by collecting OSINT from vendor reports, paste sites, dark web forums, social media, and code repos, correlating indicators, mapping adversary infrastructure with tools like Maltego and SpiderFoot, and producing structured dossiers of motivations, capabilities, infrastructure, and TTPs. Use…
building-threat-actor-profile-from-osint
Build comprehensive threat actor profiles using open-source intelligence (OSINT) techniques to document adversary motivations, capabilities, infrastructure, and TTPs for proactive defense.