identify-assumptions-new
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data provided by the user, such as product concepts, research, and business plans, creating a surface for potential instruction injection.
- Ingestion points: The skill explicitly mentions reading files (business plans, research) and product concept descriptions provided by the user in the 'Context' and 'Instructions' sections of SKILL.md.
- Boundary markers: Absent; the prompt instructions do not specify delimiters or clear separations between system instructions and user-provided data.
- Capability inventory: None; the skill does not utilize any tools or scripts for network communication, file writing, or command execution.
- Sanitization: Absent; there are no specified filters or validation steps for the content of the processed files or descriptions.
Audit Metadata