vault-concepts

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill (SKILL.md) consists exclusively of markdown instructions and metadata, containing no executable scripts, binaries, or shell commands.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing data from uncontrolled local sources.
  • Ingestion points: The agent is instructed to scan all files within the 'notes/', 'projects/', and 'resources/' directories (SKILL.md).
  • Boundary markers: The instructions lack delimiters or specific directives for the agent to ignore embedded instructions within the scanned documents (SKILL.md).
  • Capability inventory: The agent is permitted to create new files in 'notes/concepts/', update the 'index.md' file, and modify cross-references in existing notes (SKILL.md).
  • Sanitization: The skill does not provide methods for sanitizing, escaping, or validating the content read from notes before it is used to influence agent actions (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:24 PM
Security Audit — agent-trust-hub — vault-concepts