sdd-propose

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate documentation tasks within a restricted project directory structure ('openspec/'). It does not request elevated privileges, execute arbitrary commands, or perform network operations.
  • [PROMPT_INJECTION]: The skill processes untrusted data from exploration reports and external specification files, which represents an indirect prompt injection surface. This is a standard characteristic for agents designed to summarize or transform project data.
  • Ingestion points: Ingests data from exploration analysis, direct user descriptions, and existing specification files in 'openspec/specs/'.
  • Boundary markers: No explicit delimiters are defined to isolate external data from the document template instructions.
  • Capability inventory: Authorized to perform file system read/write operations and directory creation within the project scope.
  • Sanitization: External content is interpolated into the proposal template without explicit validation or sanitization routines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 12:23 AM
Security Audit — agent-trust-hub — sdd-propose