sdd-archive

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from delta specifications and merges them into main specification files without sanitization or boundary markers.\n
  • Ingestion points: Reads delta specifications from openspec/changes/{change-name}/specs/ as described in Step 2, and Engram artifacts (proposal, design, tasks) in Step 1.\n
  • Boundary markers: None present to delimit or isolate external content during the merge process into the source of truth specs.\n
  • Capability inventory: The skill performs file read, write, and directory move operations on the local filesystem (openspec/specs/).\n
  • Sanitization: No markdown sanitization or instruction filtering is applied to the content before it is merged into the project's source of truth documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:24 AM
Security Audit — agent-trust-hub — sdd-archive