building-adversary-infrastructure-tracking-system
Build an automated system to track adversary infrastructure using passive DNS, certificate transparency, WHOIS data, and IP enrichment to map and monitor threat actor command-and-control networks.
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/building-adversary-infrastructure-tracking-system/SKILL.mdSecurity
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 0.90). The provided skill requires API keys to be passed into the tracker and directly inserted into HTTP request headers (e.g., headers = {"apikey": self.st_key}), which means an LLM implementing or demonstrating this skill would need to handle and could be asked to output secret values verbatim rather than using secure env/config methods.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses data from public, untrusted third-party sources—e.g., SKILL.md and scripts/agent.py call SecurityTrails (passive DNS, reverse IP, WHOIS), crt.sh (certificate transparency), URLhaus, and ThreatFox APIs—and the code (passive_dns_lookup, pivot_from_seed, check_new_registrations, query_crtsh, build_infrastructure_map) uses those responses to pivot, discover new domains, and drive further look-up and alerting, so external content can materially influence agent decisions and follow-up actions.
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
c15f73d
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.