skills/chrissargent48/antigravity-awesome-skills/Shodan Reconnaissance and Pentesting/Gen Agent Trust Hub
Shodan Reconnaissance and Pentesting
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process service banners, HTTP headers, and metadata from arbitrary hosts on the internet, which could contain malicious instructions targeting the agent.
- Ingestion points: Data enters the agent's context through
shodan search,shodan host, and Shodan REST API calls (found in SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to treat data from Shodan results as untrusted content.
- Capability inventory: The skill performs subprocess execution of the Shodan CLI and writes data to the file system (e.g.,
shodan download,shodan parse > results.csv). - Sanitization: No sanitization or validation is applied to the service banners or HTML content retrieved from external hosts.
Audit Metadata