The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands such as ls, find, grep, sed, and comm to traverse the vault directory and analyze file relationships. These commands are used according to the skill's intended purpose for knowledge management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of markdown notes provided by the user to identify links and build index notes.
Ingestion points: Note reading operations described in SKILL.md (Steps 2, 3, and 5) and file discovery in Steps 0 and 4.
Boundary markers: Absent. The instructions do not mandate the use of delimiters or 'ignore' instructions when parsing the content of user notes.
Capability inventory: The agent has capabilities to read/write files and execute shell commands as defined in SKILL.md and README.md requirements.
Sanitization: Absent. No explicit sanitization or validation of the content within the markdown files is performed before processing.

obsidian-links