The Agent Skills Directory

[DYNAMIC_EXECUTION]: Both scripts/build_literature_canvas.py and scripts/build_literature_graph.py modify the Python module search path at runtime to load a dependency.
Evidence: The scripts use sys.path.insert(0, ...) to target a sibling directory (obsidian-project-kb-core/scripts) based on a relative path calculation.
Concern: This pattern involves executing code from computed paths outside the skill's own directory, which is a security risk if the filesystem structure is manipulated.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-controllable Obsidian notes to generate aggregated project maps, exposing a vulnerability surface.
Ingestion points: Markdown files in Sources/Papers/ and Knowledge/ are read for frontmatter and body content.
Boundary markers: No boundary markers or instructions are used to separate user data from the processing logic or to warn the agent about potential instructions within the data.
Capability inventory: The skill possesses the capability to read from and write to any file within the project vault.
Sanitization: While JSON output is structured, the build_literature_graph.py script performs direct string interpolation into Markdown and Mermaid templates using f-strings without escaping special characters or validating the content.

obsidian-literature-workflow