Skills
skills/rshankras/claude-code-apple-skills/architecture-spec/Gen Agent Trust Hub

architecture-spec

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from docs/PRD.md without input validation or boundary markers, making it susceptible to indirect prompt injection.
  • Ingestion points: docs/PRD.md (Execution Step 1).
  • Boundary markers: Absent; there are no instructions to the agent to treat the PRD content as data rather than instructions.
  • Capability inventory: The skill utilizes Read and Write tools to perform filesystem operations.
  • Sanitization: Absent; the skill extracts information from the PRD and uses it directly to populate a markdown template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:18 PM
Security Audit — agent-trust-hub — architecture-spec