find-influencers

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from both the user and external TikTok profile descriptions into the agent's context.
  • Ingestion points: User-provided niche descriptions ($ARGUMENTS) and results fetched from the mcp__apify__apify-slash-influencer-discovery-agent tool.
  • Boundary markers: The instructions do not define boundary markers (such as XML tags or triple quotes) to isolate untrusted external content from the core instructions.
  • Capability inventory: The skill is capable of executing the Apify MCP tool and rendering profile data into a markdown table.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the data returned by the external tool or provided by the user before processing.
  • [EXTERNAL_DOWNLOADS]: The skill depends on the Apify MCP server and its Influencer Discovery Agent. Apify is a well-known technology service for web scraping and automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM