publish-app
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and verify project files including
package.json,README.md, andsrc/application-config.ts. If these files are controlled by a malicious actor (e.g., in a compromised repository), they could contain instructions designed to manipulate the agent's behavior. - Ingestion points:
package.json,README.md,src/application-config.ts(SKILL.md) - Boundary markers: None identified in the prompt templates.
- Capability inventory: The skill utilizes subprocess calls to execute build and publish commands (SKILL.md).
- Sanitization: No explicit sanitization or filtering of file content is specified.
- [COMMAND_EXECUTION]: The skill recommends executing
yarn twenty dev:buildandyarn twenty app:publish. These are standard developer operations using the vendor's own CLI tools for application management.
Audit Metadata