osint
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a specialized tool to execute shell commands for reconnaissance, including utilities like
whois,dig,dnsrecon, andtheHarvester. These commands are constructed by inserting user-supplied domains and organization names into command strings. - [EXTERNAL_DOWNLOADS]: The skill fetches data from several well-known security intelligence platforms and APIs, such as
crt.sh,shodan.io,censys.io,virustotal.com,securitytrails.com, andarchive.orgto gather infrastructure and identity information. - [INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection as it ingests large volumes of untrusted data from the open web, including document metadata, archived JavaScript files, and certificate transparency logs, which are then analyzed by the agent.
- Ingestion points: External APIs (Shodan, Censys, GitHub), crt.sh logs, Wayback Machine archives, and document metadata extracted from target files.
- Boundary markers: None identified in the prompt templates.
- Capability inventory: The skill can execute shell commands via the
kalitool, perform network requests viahttp, and log findings to a local dashboard. - Sanitization: No specific sanitization or filtering of the ingested external content is described before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill dynamically generates shell commands at runtime by interpolating variables (e.g., target domains, mail servers, and API keys) into predefined command templates executed by the
kalitool.
Audit Metadata