ig-ops-pipeline
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture creates an indirect prompt injection surface by ingesting and processing untrusted content from Instagram and external scraping tools.\n
- Ingestion points: The
ig-lead-scorerworker extracts comments from Instagram posts for analysis, and theig-trend-scannerworker scrapes content from competitor accounts via Apify (SKILL.md).\n - Boundary markers: No specific boundary markers or delimiters are defined to isolate the untrusted external data from the agent's instructions during processing.\n
- Capability inventory: The pipeline has permissions to update several database tables (
ig_post_metrics,ig_lead_scores,style_library) and to send data externally to WhatsApp groups via theig-weekly-digestand optimization workers.\n - Sanitization: The instructions do not describe any sanitization, filtering, or validation steps for the external text before it is analyzed by the Claude Haiku model.
Audit Metadata