social-buisiness-explore

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructions to modify the agent's operational mode and persona.
  • Evidence: Step 6 explicitly commands the AI to "Become an Al Agent" and "repeat this process," which are role-play and logic-override patterns.
  • [PROMPT_INJECTION]: The skill ingests untrusted external data which could lead to indirect instruction execution.
  • Ingestion points: Step 6 (SKILL.md) utilizes "Google Trends" to fetch trending topics.
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded content within the fetched trends.
  • Capability inventory: Generates content (scripts, ideas) and triggers notifications (Step 6).
  • Sanitization: Absent; no validation or filtering is specified for the data retrieved from Google Trends.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:50 PM