recon-osint

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a wide array of industry-standard security reconnaissance tools, including nmap, dig, whois, gobuster, ffuf, and wpscan. These tools are used for their intended purpose of scanning and mapping target attack surfaces within an authorized security context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external systems, such as HTTP headers, website content, and DNS records gathered via WebFetch and Bash tool outputs. This creates a potential surface for indirect prompt injection if an attacker-controlled target provides malicious instructions intended to manipulate the agent's logic.
  • Ingestion points: External data processed via WebFetch and command-line outputs from curl, nmap, and other scanners.
  • Boundary markers: The skill does not define specific delimiters or warnings for the agent to ignore instructions embedded in the external data it processes.
  • Capability inventory: The skill has access to Bash (command execution), Write (file modification), and WebFetch (network access).
  • Sanitization: No explicit sanitization or filtering of external content is described in the prompt instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references and interacts with several well-known and reputable OSINT APIs and services, such as crt.sh for certificate logs, shodan.io for device discovery, and hunter.io for email patterns. These references are documented neutrally and are standard for professional security reconnaissance workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:36 PM