inkos-short-market-research
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web and user-provided samples, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill uses the
research_webtool for market analysis andingest_materialfor processing user-provided benchmarks (SKILL.md). - Boundary markers: The instructions lack explicit delimitation or prompts for the agent to ignore instructions embedded within the processed text.
- Capability inventory: The skill is limited to analysis, evaluation, and reporting; no high-privilege system operations or remote code execution capabilities are defined.
- Sanitization: There are no documented procedures for sanitizing or filtering instructions from the external content before it enters the agent's context.
Audit Metadata