Explorium Intent Signals
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were detected in the skill instructions or metadata. The skill functions as a standard integration for prospecting data.- [PROMPT_INJECTION]: The instructions are clear and instructional, focusing on the tool's intended purpose. There are no attempts to bypass safety filters or override the agent's core instructions.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses platform-provided capabilities ('explorium_api' and 'ops_tables') to handle data. No hardcoded credentials, sensitive file path access, or unauthorized network operations were found.- [INDIRECT_PROMPT_INJECTION]: The skill has a standard ingestion surface for a data tool.
- Ingestion points: Data is retrieved from the Explorium API via the 'explorium-search' action (SKILL.md).
- Boundary markers: No explicit delimiters are specified in the instructions for wrapping external data.
- Capability inventory: The skill has access to network resources ('explorium_api') and storage ('ops_tables') as defined in SKILL.md.
- Sanitization: No specific sanitization logic is described in the skill markdown.- [METADATA_POISONING]: The skill metadata correctly identifies the author and purpose without including deceptive instructions or hidden payloads.
Audit Metadata