dnsrecon

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing external DNS data, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The tool performs DNS queries (using std, axfr, brt, and srv modes) which ingest records such as TXT and SRV records from external, potentially attacker-controlled name servers.
  • Boundary markers: The instructions in SKILL.md do not specify delimiters or provide instructions for the agent to ignore instructions embedded within the retrieved DNS records.
  • Capability inventory: The skill uses the dnsrecon command-line utility to perform network reconnaissance and generates output (e.g., JSON) that is then processed by the agent.
  • Sanitization: There is no evidence of validation or sanitization of the content of the DNS records before it is returned to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:39 AM
Security Audit — agent-trust-hub — dnsrecon