markdown-vault-sync

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and analyzes untrusted codebase files (README, source code, tests, and configuration files) to synthesize documentation.\n
  • Ingestion points: Project files are read from the local repository during the survey phase.\n
  • Boundary markers: No specific instructions or delimiters are used to ensure the agent ignores or sanitizes instructions that might be embedded within the project files.\n
  • Capability inventory: The skill utilizes mcp__obsidian__vault for file creation and spawns background agents (vault-sync) for content synthesis.\n
  • Sanitization: Content extracted from the project files is processed directly without explicit sanitization or validation filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 03:20 AM