The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use shell tools like textutil and pandoc to convert resume files from the user's vault. The instruction pattern textutil -convert txt {file} does not explicitly mandate path quoting or sanitization, which creates a potential surface for command injection if a file in the vault has a maliciously crafted filename (e.g., containing semicolons or command separators).
[PROMPT_INJECTION]: The skill processes untrusted external data (resumes) and extracts information to write into configuration files. This represents an indirect prompt injection surface where malicious instructions hidden in a resume could attempt to influence the agent's behavior during the setup process.
Ingestion points: Resume files (PDF/DOCX) located in search/vault/uploads/resumes/ (identified in SKILL.md).
Boundary markers: Absent. The instructions do not tell the agent to ignore or delimit instructions found within the resume content.
Capability inventory: The skill utilizes Read, Write, Edit, and Bash tools across its scripts (identified in SKILL.md frontmatter).
Sanitization: Absent. No filtering or validation of the extracted resume text is performed before processing.

setup