reducing-aigc-detection
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates Indirect Prompt Injection by processing untrusted external documents (DOCX, PDF) using high-privilege tools.
- Ingestion points: External files are read into the agent's context during the Phase 0 reconnaissance.
- Boundary markers: Instructions do not define the use of delimiters to isolate untrusted document content from agent instructions.
- Capability inventory: The agent has access to
Bash,Write, andEdit, creating a risk if malicious instructions are hidden in target papers. - Sanitization: No validation or sanitization of input text is required by the skill logic.
Audit Metadata