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.mdfor 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
SendMessageandTaskCreatetools. - Sanitization: No evidence of sanitization or validation of the input content before it is processed by the agent team.
Audit Metadata