creative-research

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to gather and synthesize information from untrusted external sources.
  • Ingestion points: The instructions direct the agent to consume data from 'Wikis and encyclopedias', 'Community discussion' (forums), and 'Social media and interviews' (SKILL.md).
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore embedded commands within the retrieved research materials.
  • Capability inventory: The agent uses tools (implied by model-invocable: true) to perform web searches and read external site content.
  • Sanitization: Absent. There is no instruction to validate, escape, or filter the external content before including it in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 05:02 AM
Security Audit — agent-trust-hub — creative-research