influencer-creator

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Invokes a local Python script campaign-tracker.py to log and retrieve campaign history, which is essential for brand management.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external influencer profiles, creating a surface for indirect prompt injection.
  • Ingestion points: Processes influencer social media bios and brand-specific JSON configuration files.
  • Boundary markers: No explicit delimiters are specified to demarcate untrusted data.
  • Capability inventory: The agent can read local files and execute Python commands.
  • Sanitization: No sanitization or validation logic is defined for external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:03 PM