ideal-customer-profile
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a local utility,
icp_scorer.py, designed to process user-provided JSON data and generate analysis reports. This process represents a surface for potential indirect prompt injection attacks.\n - Ingestion points: Untrusted data is ingested from files specified by the user via the
--inputCLI argument.\n - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore content within the generated reports.\n
- Capability inventory: The processing script is restricted to the Python standard library and only performs file reading and data formatting; it contains no network, shell, or dynamic execution capabilities.\n
- Sanitization: The script does not perform sanitization of the values within the JSON input before rendering them into the final markdown report.\n- [COMMAND_EXECUTION]: The skill instructions guide the user to execute the
icp_scorer.pyscript locally. This execution is a documented part of the skill's intended functionality and the script itself does not perform any suspicious or unauthorized system operations.
Audit Metadata