dig
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill employs platform-specific dynamic execution placeholders (
!command) inSKILL.mdto check for thedigbinary and existence of wrapper scripts. These commands are restricted to tool versioning and file existence checks, representing safe environment discovery. - [INDIRECT_PROMPT_INJECTION]: The tool processes data from external sources (DNS records). While malicious content could be placed in DNS TXT records by an attacker, the risk is mitigated by the skill's specific focus on DNS mapping and the inclusion of a target validation hook.
- Ingestion points: DNS query results from external nameservers (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: Execution of
digand local shell scripts (SKILL.md). - Sanitization: Relies on external
PreToolUsehook validation against.pentest/scope.json.
Audit Metadata