sdd-design

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior during the design generation process.
  • Ingestion points: The skill reads proposals and specifications from the sdd/ directory, analyzes the project's existing source code in Step 2, and reads configuration rules from openspec/config.yaml.
  • Boundary markers: No explicit boundary markers or delimiters are defined to isolate untrusted content, and there are no instructions to the agent to ignore embedded commands within the source documents.
  • Capability inventory: The skill is authorized to write to the filesystem (creating design.md in openspec or hybrid modes) and persist data to the platform's artifact storage (Engram).
  • Sanitization: The skill lacks explicit sanitization, filtering, or validation steps for the content ingested from the codebase or proposal files before including it in the generated design.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:49 PM
Security Audit — agent-trust-hub — sdd-design