oracle-apex-export
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute several local Python scripts to handle validation, retention, and export logic. Evidence found in SKILL.md, references/export-retention.md, and references/release-bundle.md indicates use of scripts such as Util/scripts/validate_oracle_apex_compatibility.py and Util/scripts/manage_oracle_apex_export_retention.py.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read project-specific configuration files that define its operational parameters.
- Ingestion points: .oracle-apex-ai/project-profile.md and .oracle-apex-ai/export-policy.json (referenced in SKILL.md and references/export-retention.md).
- Boundary markers: Absent. The instructions do not specify delimiters or warnings for the content read from these files.
- Capability inventory: File system modification, subprocess execution (Python scripts), and database interaction via SQLcl.
- Sanitization: Absent. There is no mention of validating or escaping content from the configuration files before it is used by the agent.
Audit Metadata