biz-reporter
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected.
- Ingestion points: The skill ingests data from external sources including Twitter/X posts, LinkedIn posts, HubSpot CRM records, Airtable databases, and user-defined API endpoints.
- Boundary markers: There are no specified delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the retrieved data.
- Capability inventory: The skill possesses extensive capabilities including making network API calls, executing CLI tools, performing browser automation, and sending data to Slack, email, and Notion.
- Sanitization: No sanitization, validation, or filtering mechanisms are described for the external content before it is processed.
- [NO_CODE]: The skill package contains only documentation and metadata; it does not include any executable script files (Python, JavaScript, etc.) for direct inspection.
Audit Metadata