automation-pilot-command-review
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, binaries, or automated command execution logic. It serves as documentation for an AI assistant to perform code review tasks on specific JSON configuration files.
- [PROMPT_INJECTION]: The skill defines a process for reviewing untrusted user-supplied JSON configuration files, which constitutes a surface for indirect prompt injection.
- Ingestion points: The skill logic processes external
.command.json,.input.json, and.catalog.jsonfiles. - Boundary markers: There are no explicit delimiters defined in the instructions to isolate the data being reviewed from the agent's instructions.
- Capability inventory: The skill provides logic for review; however, the agent environment may have access to shell tools or file system operations.
- Sanitization: The instructions actively promote security best practices, such as requiring
toUrlEncodedandtoEscapedJsonfilters for expressions within the reviewed files.
Audit Metadata