sales-create-asset
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external data provided by the user. * Ingestion points: In 'Step 0.2: Collect Prospect Context', the agent is instructed to ingest materials like conversation transcripts, emails, notes, and call recordings. * Boundary markers: The skill lacks instructions to use delimiters or specific ignore-embedded-instruction warnings when processing these uploaded materials. * Capability inventory: The agent possesses the capability to perform web searches (Step 0.1) and generate structured file content (Self-contained HTML). * Sanitization: No sanitization, validation, or escaping of the content from the uploaded materials is mentioned in the skill instructions.
Audit Metadata