shorten
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection while processing external data.
- Ingestion points: The skill ingests untrusted text from business documents across multiple professional genres as specified in the workflow.
- Boundary markers: There are no specific delimiters or safety instructions in the prompt to isolate user input from the system instructions.
- Capability inventory: The skill is granted extensive file manipulation permissions, including Read, Write, and Edit tools, which could be leveraged if an injection occurs.
- Sanitization: No input validation or sanitization is performed on the ingested text to prevent instruction-style content from influencing the agent's operations.
Audit Metadata