harvest-adaptive

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of fetching and processing untrusted content from the web.
  • Ingestion points: External content is retrieved from user-supplied URLs using the WebFetch tool.
  • Boundary markers: There are no defined boundary markers or instructions to the agent to disregard potential instructions found within the fetched data.
  • Capability inventory: The skill utilizes highly capable tools such as Bash, Write, and WebFetch, which increases the potential impact if an injection attack succeeds.
  • Sanitization: The instructions do not specify any validation or filtering of the fetched content to prevent adversarial manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 07:46 AM
Security Audit — agent-trust-hub — harvest-adaptive