cli-anything-adguardhome
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the official AdGuard Home installation script from the AdGuardTeam GitHub repository.
- Evidence:
curl -s -S -L https://raw.githubusercontent.com/AdguardTeam/AdGuardHome/master/scripts/install.sh | sh -s -- -vinSKILL.md. - [REMOTE_CODE_EXECUTION]: The documentation includes a command pattern that pipes a remote script from a well-known service directly into the shell for installation.
- Evidence:
curl ... | shpattern used for service setup inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion point for untrusted data by retrieving DNS query logs and statistics from the network-wide ad blocker.
- Ingestion points:
cli-anything-adguardhome log showandcli-anything-adguardhome stats show. - Boundary markers: The skill encourages the use of the
--jsonflag to ensure structured data parsing by the agent. - Capability inventory: The skill is a management CLI for an external service; it does not perform dynamic execution on the data it reads.
- Sanitization: The skill provides machine-readable JSON output to minimize parsing errors of external content.
Audit Metadata