app-build-planner
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and synthesize content from external planning documents.
- Ingestion points: Step 1 in SKILL.md reads markdown files like ux-brief.md and data-model-brief.md from the docs/planning/ directory.
- Boundary markers: The instructions do not define clear delimiters or warnings to ignore instructions embedded within the planning documents.
- Capability inventory: The skill facilitates the creation of a new implementation plan file (docs/implementation-plan.md) but does not invoke shell commands, network operations, or dynamic code execution.
- Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested planning files.
- [SAFE]: The skill references framework modules and packages belonging to the Stanford Spezi project ecosystem, which are consistent with the author's identity and the skill's stated purpose.
Audit Metadata