specialist-marketing-carousel-growth-engine

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.\n
  • Ingestion points: User input is interpolated into the subagent prompt via the {the user's question} placeholder in SKILL.md.\n
  • Boundary markers: Absent; there are no delimiters (e.g., XML tags or triple quotes) or explicit instructions to treat the user input as untrusted data.\n
  • Capability inventory: The skill possesses the capability to spawn ephemeral subagents using the Agent tool.\n
  • Sanitization: Absent; no escaping, filtering, or validation is performed on the user's question before it is processed by the subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-marketing-carousel-growth-engine