Anthropic Cybersecurity Skills is a library of structured cybersecurity procedures for AI agents, covering security domains and mappings to established security frameworks. It is for authorized security analysis, penetration testing, incident response, research, defense, and education across compatible AI platforms. The catalogue entries package parts of this library as agent skills, instructions, or a plugin.
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 mukul975/Anthropic-Cybersecurity-Skills --skill analyzing-indicators-of-compromisegit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-SkillsWrote 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/mukul975/anthropic-cybersecurity-skills/analyzing-indicators-of-compromise)<a href="https://agentmods.dev/skills/mukul975/anthropic-cybersecurity-skills/analyzing-indicators-of-compromise"><img src="https://agentmods.dev/badge/skills/mukul975/anthropic-cybersecurity-skills/analyzing-indicators-of-compromise/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/mukul975/anthropic-cybersecurity-skills/analyzing-indicators-of-compromise"><img src="https://agentmods.dev/badge/skills/mukul975/anthropic-cybersecurity-skills/analyzing-indicators-of-compromise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 117 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.
- medium Data Exfiltration · line 127 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 | $0.00106 | $0.01874 |
| Opus 5 | $0.00053 | $0.00937 |
| Sonnet 5 | $0.00021 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
analyzing-indicators-of-compromise scanned grade A with 2 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 13d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "https://mb-api.abuse.ch/api/v1/", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get( Copies of this mod
8 near-identical copies found in the catalogue:
- analyzing-indicators-of-compromise — 100% identical, 0 lines differ
- analyzing-indicators-of-compromise — 86% identical, 71 lines differ
- analyzing-indicators-of-compromise — 86% identical, 23 lines differ
- analyzing-indicators-of-compromise — 84% identical, 38 lines differ
- analyzing-indicators-of-compromise — 84% identical, 59 lines differ
- analyzing-indicators-of-compromise — 84% identical, 59 lines differ
- analyzing-indicators-of-compromise — 84% identical, 59 lines differ
- analyzing-indicators-of-compromise — 84% identical, 59 lines differ
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Indicators of Compromise
When to Use
Use this skill when:
- A phishing email or alert generates IOCs (URLs, IP addresses, file hashes) requiring rapid triage
- Automated feeds deliver bulk IOCs that need confidence scoring before ingestion into blocking controls
- An incident investigation requires contextual enrichment of observed network artifacts
Do not use this skill in isolation for high-stakes blocking decisions — always combine automated enrichment with analyst judgment, especially for shared infrastructure (CDNs, cloud providers).
Prerequisites
- VirusTotal API key (free or Enterprise) for multi-AV and sandbox lookup
- AbuseIPDB API key for IP reputation checks
- MISP instance or TIP for cross-referencing against known campaigns
- Python with
requestsandvt-pylibraries, or SOAR platform with pre-built connectors
Workflow
Step 1: Normalize and Classify IOC Types
Before enriching, classify each IOC:
- IPv4/IPv6 address: Check if RFC 1918 private (skip external enrichment), validate format
- Domain/FQDN: Defang for safe handling (
evil[.]com), extract registered domain via tldextract - URL: Extract domain + path separately; check for redirectors
- File hash: Identify hash type (MD5/SHA-1/SHA-256); prefer SHA-256 for uniqueness
- Email address: Split into domain (check MX/DMARC) and local part for pattern analysis
Defang IOCs in documentation (replace . with [.] and :// with [://]) to prevent accidental clicks.
Step 2: Multi-Source Enrichment
VirusTotal (file hash, URL, IP, domain):
import vt
client = vt.Client("YOUR_VT_API_KEY")
# File hash lookup
file_obj = client.get_object(f"/files/{sha256_hash}")
detections = file_obj.last_analysis_stats
print(f"Malicious: {detections['malicious']}/{sum(detections.values())}")
# Domain analysis
domain_obj = client.get_object(f"/domains/{domain}")
print(domain_obj.last_analysis_stats)
print(domain_obj.reputation)
client.close()
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.
- 13d ago First seen · 194 lines · 106 tokens per session scan A 4d6ef90f4bbd
analyzing-indicators-of-compromise is a skill published in the GitHub repository mukul975/Anthropic-Cybersecurity-Skills (32,631 stars, last pushed 12d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,874 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-indicators-of-compromise
Use when analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…
analyzing-indicators-of-compromise
A guide for investigating indicators of compromise, or signs such as suspicious IP addresses, domains, URLs, file fingerprints, and email addresses. It combines information from several security-intelligence services.
analyzing-indicators-of-compromise
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…
analyzing-indicators-of-compromise
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…
analyzing-indicators-of-compromise
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…
analyzing-indicators-of-compromise
Analyzes indicators of compromise (IOCs) including IP addresses, domains, file hashes, URLs, and email artifacts to determine maliciousness confidence, campaign attribution, and blocking priority. Use when triaging IOCs from phishing emails, security alerts, or external threat feeds; enriching raw IOCs with…