get-results
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
covalcommand-line interface to interact with simulation data. It executes commands such ascoval simulations list,coval simulations get, andcoval simulations audioto retrieve metadata, transcripts, and audio files. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (simulation transcripts and error messages) which could contain malicious instructions designed to influence the agent's behavior during analysis.
- Ingestion points: Simulation data, including transcripts and error messages, are fetched via the
covalCLI and analyzed by the agent. - Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious content within the transcripts.
- Capability inventory: The skill has the ability to execute shell commands via the
covalCLI and download files to the local system. - Sanitization: No explicit sanitization or validation of the retrieved simulation content is mentioned before it is presented to or processed by the agent.
Audit Metadata