game-market-research
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites via web search and fetch tools, creating a vulnerability surface for instructions embedded in external content to influence the agent.
- Ingestion points: Phases 1, 2, and 5 utilize
WebSearchandWebFetchto retrieve genre, competitor, and trend data from various external web sources. - Boundary markers: The instructions do not define specific delimiters or directives to ignore potentially malicious instructions found within the fetched content.
- Capability inventory: The skill is permitted to use the
Writetool to save research briefs to thedesign/market-research/directory, and it also has access toRead,Glob, andGreptools. - Sanitization: The workflow lacks explicit steps to sanitize, escape, or validate external content before it is processed by the agent and written to the filesystem.
Audit Metadata