design-register-bootstrap
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external, potentially untrusted data to inform the creation of design documentation.
- Ingestion points: The skill instructions in
SKILL.mdandSKILL_CARD.mddirect the agent to read "user briefs," "reference URLs," and other external project artifacts. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external input as untrusted or to ignore instructions embedded within those inputs.
- Capability inventory: The skill has the capability to create or update local files such as
PRODUCT.mdandDESIGN.mdbased on the processed information. - Sanitization: The skill does not define specific sanitization or validation logic for the external content before it is used to generate documentation.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration without any executable scripts, binaries, or automated shell commands.
Audit Metadata