competitive-teardown

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves gathering competitor information from external sources via web research. This introduces a risk where the agent could be influenced by instructions hidden in the processed data.
  • Ingestion points: The skill ingests data from external websites (screenshots, walkthroughs, app store listings, or public design write-ups) in the first step of the workflow.
  • Boundary markers: No explicit boundary markers or instructions to disregard embedded commands in the researched data are present to prevent the agent from obeying instructions found in external content.
  • Capability inventory: The agent is authorized to perform scoped, reversible edits to the current Figma design file and generate recommendations based on the research findings.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content gathered from the web before it is used to generate design recommendations or file edits.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:31 AM
Security Audit — agent-trust-hub — competitive-teardown