cavuno-board-account

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data processing features.\n
  • Ingestion points: The skill ingests untrusted data via the resume upload and parsing workflow (board.me.resume.upload) in SKILL.md.\n
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are provided to handle parsed resume content.\n
  • Capability inventory: The agent has access to powerful tools, including account deletion (board.me.delete) and profile modification.\n
  • Sanitization: There is no evidence of sanitization or schema validation for the data ingested from parsed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:07 AM
Security Audit — agent-trust-hub — cavuno-board-account