munger-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its data ingestion workflow.
  • Ingestion points: The workflow in SKILL.md requires the agent to use web search tools to gather current information from external sources.
  • Boundary markers: The instructions do not specify the use of delimiters or clear separation between the agent's instructions and the untrusted data fetched from the web.
  • Capability inventory: The agent has the capability to perform network requests via search tools and then use that information to generate complex, opinionated responses.
  • Sanitization: There are no measures provided to sanitize or validate the content retrieved from the internet before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 08:53 AM