vault-index

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface
  • Ingestion points: The skill reads content from the notes/, projects/, and resources/ directories to build an index (SKILL.md).
  • Boundary markers: Absent; there are no specific instructions or delimiters used to ensure the agent ignores potential commands embedded within the scanned vault files.
  • Capability inventory: The skill is authorized to modify the index.md file based on retrieved content (SKILL.md).
  • Sanitization: Absent; the workflow does not include steps to sanitize, escape, or validate the content of the files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:33 AM
Security Audit — agent-trust-hub — vault-index