hap-cli
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'hap-cli' package from the official Python Package Index using 'pip install hap-cli'. This is the standard method for deploying the vendor's command-line interface.
- [COMMAND_EXECUTION]: The core functionality of the skill involves executing 'hap' commands in the terminal. These commands facilitate authentication ('hap auth login'), configuration ('hap app select'), and platform operations ('hap chat send', 'hap worksheet record create').
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to read and process data from external sources within the HAP platform, which could potentially contain malicious instructions.
- Ingestion points: Commands like 'hap chat messages', 'hap worksheet record get', and 'hap approval todo' read content from external databases and user-generated communications.
- Boundary markers: The instructions do not explicitly provide delimiters or warnings for the agent to ignore instructions embedded in the retrieved data.
- Capability inventory: The skill possesses capabilities to write data, such as 'hap upload' for file transfers, 'hap chat send-to-group' for messaging, and 'hap worksheet record update' for data modification.
- Sanitization: There are no instructions for sanitizing or escaping the data retrieved from the HAP platform before the agent processes it.
Audit Metadata