memory-to-obsidian
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill establishes a workflow for ingesting untrusted user data and storing it in a persistent file system, which may be referenced by the agent in future contexts, leading to potential indirect prompt injection. * Ingestion points: User-provided thoughts and notes via the memory command in SKILL.md. * Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore instructions within the saved content. * Capability inventory: File-system write access to the user's Obsidian vault. * Sanitization: Absent; the skill does not specify any validation or filtering of the input content.
- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata without any attached scripts, executables, or background processes.
Audit Metadata