persona-researcher

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and organize research papers and notes from Google Drive which could contain adversarial instructions.
  • Ingestion points: Reads files and research papers from Google Drive folders as described in SKILL.md.
  • Boundary markers: No delimiters or instructions are provided to help the agent distinguish between its system instructions and the content of the research papers.
  • Capability inventory: The agent is authorized to write Google Docs, append to Sheets, and send emails via Gmail (SKILL.md).
  • Sanitization: There is no mention of sanitizing or validating the content read from external files before using it in actions like email sending.
  • [NO_CODE]: The skill consists solely of markdown instructions and does not contain any executable scripts, binaries, or configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 12:26 PM