game-market-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources using the
WebSearchandWebFetchtools during several research phases, including genre analysis, competitor review analysis, and community signal detection. This external content could contain hidden instructions aimed at influencing the agent's final report or behavior. - Ingestion points: Phased research steps (Phase 1 through Phase 5) in
SKILL.mdthat utilizeWebSearchandWebFetchto retrieve competitor data, player reviews, and forum discussions. - Boundary markers: The instructions do not specify the use of delimiters or specific prompts to ignore instructions embedded within the fetched external data.
- Capability inventory: The skill utilizes
Read,Glob,Grep,Write,WebSearch, andWebFetch. It has the ability to write analysis results to the local filesystem (design/market-research/). - Sanitization: There are no explicit mentions of content sanitization, filtering, or validation for the data retrieved from external URLs before it is processed by the agent.
Audit Metadata