build-with-tinybase
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
npm create tinybase@latestfor project scaffolding and anode -escript to inspect package exports in thenode_modulesdirectory. - [EXTERNAL_DOWNLOADS]: Fetches generators and dependencies from the npm registry and retrieves documentation from
tinybase.org. - [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading local project files and remote documentation, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points:
package.json,AGENTS.md,README.md, and documentation fromhttps://tinybase.org/llms.txt. - Boundary markers: No specific boundary markers or instructions to disregard embedded commands are present in the provided templates.
- Capability inventory: The skill can execute shell commands, manage files, and interact with network resources.
- Sanitization: No sanitization or input validation logic is applied to the content of the ingested files.
Audit Metadata