The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a bash script scripts/read-vault-file.sh that executes the cat command to read files from the local filesystem.
[COMMAND_EXECUTION]: Path Traversal vulnerability in scripts/read-vault-file.sh. The script fails to sanitize the filename argument before use, enabling access to sensitive files outside the intended vault directory (e.g., /etc/passwd) using relative paths or absolute paths.
[PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface. The skill is designed to read and interpret content from an Obsidian vault which can contain untrusted data.
Ingestion points: Files located within the hardcoded vault path /Users/kriscard/obsidian-vault-kriscard.
Boundary markers: None; the skill lacks specific markers to delimit or ignore instructions embedded within vault content.
Capability inventory: File reading capabilities via cat (within scripts/read-vault-file.sh) and the obsidian read command.
Sanitization: None; no validation or escaping of external content is performed before the agent processes the data.

vault-structure