game-development
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform research by browsing and reading content from external sources such as official store pages, guides, wikis, fandom pages, and reviews. These third-party sites are often user-editable or attacker-controllable, providing a vector for malicious instructions to be ingested into the agent context.
- Ingestion points:
SKILL.md(Research section) instructs reading external web pages. - Boundary markers: The skill does not provide instructions to delimit or ignore potential commands within the external data.
- Capability inventory: The agent possesses browser access and the ability to write files (source code, assets) and execute commands in the environment.
- Sanitization: The instructions do not specify a need to sanitize or validate the content retrieved from external sources before processing.
Audit Metadata