munger

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data and using it to prompt sub-agents without sufficient isolation or sanitization.
  • Ingestion points: User-supplied business ideas are accepted through $ARGUMENTS and AskUserQuestion. Additionally, the 'Moat Analyst' sub-agent fetches external data using WebSearch and WebFetch.
  • Boundary markers: The skill lacks explicit delimiters or instructions for sub-agents to ignore potentially malicious content within the user-provided [IDEA] or [full description] variables.
  • Capability inventory: The skill and its agents have access to powerful tools including Bash, Write, Edit, WebSearch, WebFetch, Agent, and TeamCreate.
  • Sanitization: There is no evidence of sanitization or validation of the input before it is interpolated into the prompts for the specialized analysis agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 11:52 PM