obsidian-notes-creator
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (source material), which could contain malicious instructions designed to influence the agent's behavior. \n
- Ingestion points: External source material, such as lecture notes and PDFs, as defined in
SKILL.md. \n - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to treat external content as untrusted data or to ignore embedded instructions. \n
- Capability inventory: The agent is guided to generate and run Python code that performs local file writes (e.g., to
99-assets/figure.svg) as described inreferences/components/diagrams.md. \n - Sanitization: There are no instructions for sanitizing, escaping, or validating the input source material before it is incorporated into notes or visuals. \n- [DYNAMIC_EXECUTION]: The skill provides a Python script template in
references/components/diagrams.mdfor generating SVG files. This facilitates the generation and execution of code by the agent to create visual assets on the local filesystem.
Audit Metadata