etl-connector-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external, potentially untrusted business data to validate product demand, creating an attack surface for indirect prompt injection.\n- Ingestion points: The agent is instructed to collect evidence from support tickets, lost-deal notes, API logs, and security/procurement questionnaires (SKILL.md, Section 1).\n- Boundary markers: The skill does not provide specific instructions to use delimiters or ignore embedded prompts within these external data sources.\n- Capability inventory: The skill is limited to providing strategic text output and does not possess capabilities for network operations, file system modifications, or shell command execution.\n- Sanitization: No sanitization, filtering, or validation logic for the external evidence is defined in the instructions.
Audit Metadata