bruno-new-endpoint

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from the web using WebFetch.
  • Ingestion points: API documentation is fetched from external sources in Step 1.
  • Boundary markers: The skill lacks delimiters or explicit instructions for the agent to ignore potentially malicious instructions embedded in the fetched content.
  • Capability inventory: The agent reads existing .bru files and creates new files through the /bruno skill.
  • Sanitization: No sanitization or validation of the external documentation is performed before it influences file creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:39 AM
Security Audit — agent-trust-hub — bruno-new-endpoint