recon
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute network reconnaissance utilities such as dig, whois, and nmap. It incorporates user-provided arguments directly into these shell commands, which requires the agent to handle input safely to prevent command injection.
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to crt.sh, a well-known certificate transparency service, to enumerate subdomains. This is an expected and neutral operation for a reconnaissance tool.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from various external sources which could contain malicious instructions.
- Ingestion points: Data is retrieved from DNS records, WHOIS responses, and web content via WebFetch and curl (Phase 1 and 2 in SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands when the agent processes or reports on this external data.
- Capability inventory: The agent has capabilities including Bash execution, file writing, and network access (allowed-tools: Bash, Read, Write, WebSearch, WebFetch).
- Sanitization: There are no explicit instructions for the agent to sanitize, validate, or filter the content retrieved from external sources before including it in the Recon Report context.
Audit Metadata