performance-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external marketing data provided via MCP connections or manual input.
- Ingestion points: Performance data described in 'Phase 1: Data Collection'.
- Boundary markers: The skill uses a structured output format which helps compartmentalize data, though explicit delimiters for raw input are not defined in the instructions.
- Capability inventory: The skill instructions do not utilize any high-risk capabilities such as file writing, shell command execution, or network requests.
- Sanitization: No specific sanitization logic is present, but the risk is low given the restricted scope of the agent's actions (generating a text-based report).
Audit Metadata