design-review
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODECOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and interpret external documents.
- Ingestion points: The skill instructions in
SKILL.mddescribe reading files from the filesystem via the/design-review [path/to/document.md]command. - Boundary markers: There are no defined delimiters or 'ignore instructions' warnings to prevent the agent from executing malicious commands embedded within the design documents it reviews.
- Capability inventory: The skill's primary function involves reading files directly from the host filesystem.
- Sanitization: No sanitization or validation logic is specified for the content of the documents being processed.
- [NO_CODE]: The skill is composed entirely of markdown documentation and YAML metadata; it does not include any Python, JavaScript, or other executable scripts.
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to access and read files from the local filesystem to perform its auditing and review tasks.
Audit Metadata