thesis-advisor

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (user manuscripts, reference lists) which could contain indirect prompt injection instructions.
  • Ingestion points: Phase 1 extracts user inputs and existing materials, saving them to _workspace/00_input.md for subsequent agent consumption.
  • Boundary markers: There are no explicit instructions to use XML tags or delimiters to isolate user-provided content from agent instructions.
  • Capability inventory: The skill utilizes file system writes to a workspace directory and inter-agent communication via SendMessage and TaskCreate tools.
  • Sanitization: No evidence of sanitization or validation of the input content before it is processed by the agent team.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 05:16 AM
Security Audit — agent-trust-hub — thesis-advisor