skills/csark0812/toolbox/domain-model/Gen Agent Trust Hub

domain-model

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation templates (glossary-format.md, adr-format.md) and schemas (output-schema.md) from the author's repository on GitHub (csark0812/toolbox).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and updates existing architectural decision records and glossary files from the repository, creating a surface for indirect prompt injection from data at rest.
  • Ingestion points: Reads existing repository files during the 'Dedupe or update in place' step in SKILL.md.
  • Boundary markers: The skill does not define specific boundary markers or 'ignore' instructions for the content read from files.
  • Capability inventory: The skill has capabilities to read and write markdown files within the repository context.
  • Sanitization: There is no evidence of sanitization or content validation for the data read from existing files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:17 PM
Security Audit — agent-trust-hub — domain-model