table-creation
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a shell command to verify that the EXTRUCT_API_TOKEN is correctly set in the environment.
- [EXTERNAL_DOWNLOADS]: API documentation is retrieved from the official vendor domain at https://www.extruct.ai/docs to ensure compatibility.
- [DATA_EXFILTRATION]: Parsed company information is sent to the official Extruct API endpoint at https://api.extruct.ai/v1 for processing.
- [PROMPT_INJECTION]: The skill processes untrusted user data which introduces a surface for indirect prompt injection.
- Ingestion points: The skill ingests data from user-provided CSV files and freeform pasted text lists.
- Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to distinguish user data from instructions.
- Capability inventory: The skill can execute shell commands and perform network POST operations to a vendor API.
- Sanitization: The skill performs basic extraction of domains from URLs but does not sanitize metadata fields for potential injection patterns.
Audit Metadata