moc-update
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) due to its core functionality of processing untrusted data to perform file-system writes.
- Ingestion points: The skill reads note titles and content from the local vault via
obsidian_rag_queryandobsidian_search_notes(SKILL.md). - Boundary markers: There are no instructions defining delimiters or specifically warning the agent to ignore instructions embedded within the user notes.
- Capability inventory: The skill has the ability to modify the local file system using
obsidian_insert_at_headingandobsidian_append_note(SKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the content ingested from external notes before it is used to generate summaries or links.
Audit Metadata