gsp-spec-driven-planning
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of persistent project artifacts like design documents and task lists based on user input. This process involves a vulnerability surface where malicious user instructions could be stored in the repository and influence downstream agent behaviors.\n
- Ingestion points: User-provided goals, scope definitions, and requirements are ingested during the planning workflow (SKILL.md).\n
- Boundary markers: There are no explicit delimiters or boundary instructions defined to isolate external user input from the rest of the documentation content.\n
- Capability inventory: The skill uses tools to create and update multiple files within the repository's
specs/andchanges/folders.\n - Sanitization: The skill does not provide instructions for sanitizing, validating, or filtering user input before it is written to the repository.
Audit Metadata