apexlang-26-1
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation describes the use of local scripts and binaries to manage the Oracle APEX application lifecycle. These executions are core to the skill's primary purpose.
node tools/apexctl.mjs: A local JavaScript utility used for application generation and validation.scripts/validate-apex-app.sh: A shell script that executes SQLcl commands to validate application integrity.scripts/deploy-apex-app.sh: A shell script that executes SQLcl commands to import applications into a database.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external application data, which presents an attack surface for indirect prompt injection via malicious application source files.
- Ingestion points: The skill reads application directories,
.apxsource files, and example applications during the generation and deployment processes inSKILL.md. - Boundary markers: The instructions emphasize gated validation and an explicit human-in-the-loop approval step for imports.
- Capability inventory: The skill utilizes shell script execution and Node.js for filesystem interaction and database deployment.
- Sanitization: The documentation mentions the use of generation contracts, templates, and grammar-backed syntax checks to maintain data integrity.
Audit Metadata