managing-pi-hole
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a shell function
pihole_cmdthat executes commands on a remote host via SSH. The use of$*without quoting or sanitization allows for potential command injection if malicious arguments are passed to the function. - [INDIRECT_PROMPT_INJECTION]: The skill processes DNS query logs and domain statistics from the Pi-hole API. This creates an attack surface where malicious instructions embedded in domain names or log entries could influence the agent's behavior.
- Ingestion points: Pi-hole API responses for query logs and top blocked domains in SKILL.md.
- Boundary markers: Absent; there are no specific delimiters or instructions to treat log data as untrusted content.
- Capability inventory: Remote shell access via SSH, network requests via Curl, and local utility execution (jq, sort, etc.) as defined in SKILL.md.
- Sanitization: Absent; domain names and log entries are parsed and output directly to the agent's context without filtering.
Audit Metadata