tam-builder
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources which may contain malicious instructions.
- Ingestion points: Reads ICP criteria from local answer sheets and retrieves company records from the Clay platform via the clay search command.
- Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions embedded in the search results.
- Capability inventory: The skill executes shell commands using the clay CLI.
- Sanitization: There is no explicit logic to sanitize or escape data retrieved from search results before it is handled by the agent.
- [COMMAND_EXECUTION]: The skill relies on shell commands for its core functionality.
- Evidence: Uses commands such as clay whoami and clay search to interact with the Clay environment.
- Context: These commands utilize the official CLI for the platform (clay-run), representing standard vendor-provided functionality.
Audit Metadata