arkcli-models
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data returned by the
arkclitool, such as model names, descriptions, and metadata. This introduces a surface for indirect prompt injection if the remote registry contains adversarial content designed to influence the agent's behavior. - Ingestion points: Results from
arkcli models listandarkcli models searchinSKILL.mdand referenced files. - Boundary markers: None explicitly mentioned in the scripts for model data processing.
- Capability inventory: Command execution via
arkcliand local script execution usingpython3. - Sanitization: The provided processing scripts in
references/arkcli-models-list.mddo not sanitize string fields before outputting them to the agent context. - [DYNAMIC_EXECUTION]: The skill provides a Python script template in
references/arkcli-models-list.mdfor the agent to execute locally. This script is intended to filter and process JSON output where the CLI tool lacks server-side filtering capabilities. - Evidence: A bash heredoc pattern in
references/arkcli-models-list.mdthat pipes a multi-line Python script topython3 -to handle date parsing and item filtering.
Audit Metadata