upsell-downsell-scripting
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on user-supplied information from discovery and planning questions to generate sales scripts, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the data.
- Ingestion points: SKILL.md defines a workflow that ingests user answers to ten discovery and planning questions.
- Boundary markers: Absent; the skill instructions do not utilize delimiters or specific instructions to the agent to ignore potentially malicious content within user inputs.
- Capability inventory: None; the skill does not use network tools, file system access, or command execution capabilities.
- Sanitization: Absent; there are no mechanisms described for filtering or sanitizing user-provided text before processing.
- [NO_CODE]: The skill consists entirely of markdown instructions and templates for natural language generation by the AI agent. It does not include any referenced scripts, executables, or binary files.
Audit Metadata