specialized-cultural-intelligence-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze external content such as code, UI designs, and marketing copy provided by users. This creates a surface area for indirect prompt injection where instructions embedded within the analyzed material could potentially influence the agent's behavior.
- Ingestion points: The workflow defined in
SKILL.md('Phase 1: The Blindspot Audit') ingests code, copy, prompts, and UI designs as primary input for analysis. - Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded in the source material.
- Capability inventory: The skill body focuses on research and reporting; the included
run.shscript executes a local Python runner, but the skill itself does not request or use dangerous tools like network access or file writes in the provided instruction set. - Sanitization: There is no evidence of input validation or sanitization routines for the data being analyzed.
Audit Metadata