flpbalada-cognitive-biases
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided product designs, user journey maps, and behavioral data. This creates a surface for indirect prompt injection where malicious instructions embedded in the analyzed data could attempt to influence the agent's output formatting or analysis logic.
- Ingestion points: User-provided descriptions of product features and decision-point maps defined in the 'Bias Analysis Framework' section.
- Boundary markers: The skill uses a structured markdown output template but does not specify delimiters for the input data being analyzed.
- Capability inventory: The skill is restricted to generating text-based reports; it does not utilize system tools, network operations, or file-writing capabilities.
- Sanitization: No explicit input sanitization or validation of the ingested data is described.
- [SAFE]: The external links provided in the 'Resources' section point to well-known educational sites and published literary works related to psychology and design (e.g., Goodreads, Growth.Design). These references are informational and do not involve code execution or automated downloads.
Audit Metadata