Shodan Reconnaissance and Pentesting
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation extensively lists commands for the Shodan CLI, such as
shodan search,shodan scan, andshodan host. These are intended to be executed by the agent to perform its primary function of network reconnaissance. - [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the legitimate
shodanpackage viapipand the Arch Linux package managerpacman. These are standard installation procedures for a well-known security tool. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from the Shodan API (e.g., banners, HTML titles, and hostnames), which are untrusted external sources.
- Ingestion points: Data enters the system via
shodan searchandapi.search()insub-skills/3-search-queries.mdandsub-skills/example-5-python-automation-script.mdrespectively. - Boundary markers: None are used to separate the external data from the agent's instructions.
- Capability inventory: The provided scripts only demonstrate printing the data to the console; no high-risk capabilities like writing to the filesystem or executing secondary commands based on the data are present.
- Sanitization: No sanitization or escaping of the retrieved data is performed before it is processed by the agent.
Audit Metadata