create-note
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read and process the contents of existing Obsidian vault notes, daily logs, and index files to promote or synthesize information. This creates an indirect prompt injection surface where malicious instructions embedded within notes could influence the agent's behavior during the synthesis process.
- Ingestion points: Processes arbitrary note content from the vault directory, daily notes, and index files as specified in SKILL.md and references/promote-mode.md.
- Boundary markers: The instructions do not specify the use of boundary markers or delimiters for the ingested note content to distinguish it from the agent's instructions.
- Capability inventory: The agent has the ability to read from and write to the local file system (Obsidian vault) via the 'safe-write flow' mentioned in SKILL.md and references/promote-mode.md.
- Sanitization: The skill relies on manual user approval ('Preview, write, and verify') rather than automated sanitization of ingested content.
Audit Metadata