skills/open-gsd/gsd-core/gsd-ui-phase/Gen Agent Trust Hub

gsd-ui-phase

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources which could contain malicious instructions.
  • Ingestion points: The skill reads ~/.claude/gsd-core/workflows/ui-phase.md, ~/.claude/gsd-core/references/ui-brand.md, and processes user-supplied $ARGUMENTS.
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill is permitted to use Bash, Agent, Write, and WebFetch tools as specified in the allowed-tools metadata.
  • Sanitization: There is no evidence of sanitization or input validation for the data retrieved from the files or arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-ui-phase