AsnRecon

Fail

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The workflow workflows/FullAsnRecon.md contains a shell command that directly interpolates the user-provided {company_name}: curl -s "https://bgp.he.net/search?search[search]={company_name}" | grep -oP 'AS\d+' | sort -u. A malicious user could provide a company name value containing shell metacharacters (e.g., "; rm -rf /; #) to execute arbitrary commands on the system.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes data from an external source, which could allow for indirect prompt injection if that source were to return malicious instructions.
  • Ingestion points: Data is retrieved from bgp.he.net via search and prefix table fetches as defined in workflows/FindAsn.md, workflows/FindIpRanges.md, and workflows/FullAsnRecon.md.
  • Boundary markers: The prompts lack boundary markers or explicit instructions to treat the external content as untrusted data.
  • Capability inventory: The skill has the capability to execute shell commands and write files to the local file system.
  • Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill fetches network and routing data from bgp.he.net, a well-known service for BGP reconnaissance and IPv4 prefix lookups.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Nov 16, 2026, 12:04 PM