influencer-evaluator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses a vulnerability surface for indirect prompt injection because it ingests and processes untrusted data from external sources.\n
  • Ingestion points: The skill uses WebSearch and WebFetch to retrieve information from Instagram, YouTube, and TikTok profiles.\n
  • Boundary markers: The instructions lack delimiters or specific warnings to ignore instructions that might be embedded in the fetched profile bios or comments.\n
  • Capability inventory: The skill is capable of performing web searches, fetching page content, and writing files to the local directory ~/.claude/cache/influencer/.\n
  • Sanitization: No explicit sanitization or filtering is applied to external content before it is processed or used to generate final reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM