NYC

influencer-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill identifies the need for external data retrieval using standard libraries like requests and beautifulsoup4 for scraping public influencer profiles on Twitter, Substack, and YouTube. This behavior is transparent and aligns with the skill's functional description.
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface Analysis:
  • Ingestion points: Data is ingested via Perplexity API and web scraping from external influencer platforms as described in SKILL.md.
  • Boundary markers: Absent. The skill lacks specific instructions to delimit untrusted web content or to ignore embedded instructions within that content.
  • Capability inventory: Uses Anthropic's LLM for content pattern analysis and provides a CLI entry point via scripts/analyze_influencer.py for local processing.
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM