lit-review

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection through user-supplied input.
  • Ingestion points: Research topics, questions, or draft papers provided by the user in Step 1.
  • Boundary markers: Absent. There are no instructions for the agent to distinguish between the research data and instructions, making it possible for a malicious 'draft paper' to redirect the agent's tasks.
  • Capability inventory: Uses WebSearch, WebFetch, Write, and Task, which could be abused if an injection occurs (e.g., forcing searches to malicious domains or writing unauthorized files).
  • Sanitization: No sanitization or validation of the input content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 10:39 AM