archive-artifacts

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard archival procedures using local file operations and metadata management. All operations are scoped to the project directory.\n- [PROMPT_INJECTION]: An indirect prompt injection surface exists where the skill reads markdown documentation and interpolates it into design files.\n
  • Ingestion points: Metadata and markdown content are read from slice directories (brief.md, blueprint.md) in scripts/archive_data.py.\n
  • Boundary markers: The summary blocks in system-design.md are delimited by HTML comments (e.g., <!-- archived-slice-summaries:start -->).\n
  • Capability inventory: The skill writes to system-design.md and delegates directory relocation to an external execution component.\n
  • Sanitization: Content extraction is performed via regex; no additional sanitization or escaping of the ingested text is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 07:38 PM