skills/mukul975/anthropic-cybersecurity-skills/collecting-open-source-intelligence/Gen Agent Trust Hub
collecting-open-source-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs network operations to gather threat intelligence from well-known services, including Shodan, SecurityTrails, crt.sh, and GitHub. These operations are consistent with the skill's stated purpose and follow standard OSINT practices.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses and user-supplied domain names, creating a surface for potential indirect prompt injection.
- Ingestion points: Target domains and responses from Shodan, crt.sh, SecurityTrails, and GitHub APIs in
scripts/agent.py. - Boundary markers: Absent in the processing logic; instructions do not explicitly warn the model to disregard instructions embedded in external data.
- Capability inventory: Network requests (
requests.get) and local file writing (json.dump) inscripts/agent.py. - Sanitization: No specific input validation or output escaping is performed on external content or user-provided domain strings.
Audit Metadata