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, andsrvmodes) which ingest records such as TXT and SRV records from external, potentially attacker-controlled name servers. - Boundary markers: The instructions in
SKILL.mddo not specify delimiters or provide instructions for the agent to ignore instructions embedded within the retrieved DNS records. - Capability inventory: The skill uses the
dnsreconcommand-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