cocos-build
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curl.exeto send a request tohttp://localhost:7456/update-db, which is the local API endpoint for Cocos Creator to refresh its asset database. This is a routine developer workflow operation. - [INDIRECT_PROMPT_INJECTION]: The skill monitors and acts upon files within the
assets/directory. Any tool that ingests files created or modified by users or external sources has a theoretical attack surface for indirect prompt injection, though here the risk is limited to the local development environment. - Ingestion points: Reads files from the
assets/directory (SKILL.md). - Boundary markers: None identified.
- Capability inventory: Executes shell commands via
curl.exeand interacts with a local web service. - Sanitization: None identified.
Audit Metadata