component-scaffold
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the repository to determine scaffolding conventions.
- Ingestion points: Reads
REPO_PROFILE.jsonand existing component files from the filesystem. - Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions when reading repository-provided configuration.
- Capability inventory: Performs filesystem writes to create new components and modify export files.
- Sanitization: Absent; the workflow instructs the agent to infer patterns directly from existing code and follow external configuration without validation.
Audit Metadata