Apify Results Query

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to the way it processes user-provided filtering criteria.
  • Ingestion points: The filter_description input in SKILL.md allows users to provide natural language that is directly translated into SQL-compatible logic.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard malicious commands embedded within the filter_description or the scraped data from the apify_mapped_records table.
  • Capability inventory: The skill utilizes the apify-admin edge function to perform database queries (action: 'query_results') based on the generated filters.
  • Sanitization: The instructions do not specify any sanitization, escaping, or validation steps for the natural language input before it is transformed into a query, relying solely on the agent's translation capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM