icp-matrix-builder
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
clayCLI tool to verify user identity and retrieve platform-specific taxonomy metadata, storing the results in temporary local files. - [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user-provided descriptions of Ideal Customer Profiles and data from external answer sheets.
- Ingestion points: User input fields for company axes, persona axes, and qualifiers, as well as external answer sheet files.
- Boundary markers: The skill does not define explicit delimiters or use specific instructions to ignore embedded commands within the ingested data.
- Capability inventory: The agent can execute CLI commands and perform file system operations such as reading local sheets and writing temporary files.
- Sanitization: The skill translates input into a closed taxonomy, which serves as a logical filter, but it lacks formal sanitization at the intake stage.
Audit Metadata