gsd-ui-phase
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data via user-supplied arguments ($ARGUMENTS) and the output of the 'gsd-ui-researcher' tool without explicit boundary markers. * Ingestion points: Phase number arguments and external research data in SKILL.md. * Boundary markers: No delimiters or ignore instructions are present for interpolated data. * Capability inventory: The skill utilizes Bash, Write, and Agent tools to perform its tasks. * Sanitization: No validation or escaping of external content is specified.
- [SAFE]: The skill accesses execution contexts and references located at ~/.claude/gsd-core/, which are associated with the skill author's own framework and project structure.
Audit Metadata