launch-positioning-builder

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes data from external, untrusted competitor websites via the fetch_webpage tool.
  • Ingestion points: The agent uses fetch_webpage and web_search to retrieve data from user-provided competitor and product URLs.
  • Boundary markers: The instructions do not include specific delimiters or guidelines to ignore instructions that might be embedded within the external content.
  • Capability inventory: The skill has access to web_search, fetch_webpage, and file-writing capabilities to generate and store output documents on the local file system.
  • Sanitization: There is no evidence of sanitization or validation for the content retrieved from external sources before it is analyzed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:03 PM