The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's SKILL.md file suggests an optional validation step using the command python3 scripts/validate_output.py "<markdown-output>". Because the agent's output is derived from untrusted user notes and files, this creates a shell command injection vector. A malicious file could be crafted to include shell metacharacters (e.g., backticks, $(...), or ;) which, when included in the agent's response and passed to the shell, would execute arbitrary code on the host system.
[PROMPT_INJECTION]: The skill facilitates indirect prompt injection by processing external data and using it to trigger a shell-based capability without adequate protection.
Ingestion points: Content from user-provided files and notes processed in SKILL.md and references/workflow.md.
Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore instructions found within the files being organized.
Capability inventory: Shell execution via python3 scripts/validate_output.py as defined in the SKILL.md quick start instructions.
Sanitization: Absent. The skill provides no instructions for the agent to sanitize or escape its markdown output before using it as a command-line argument.

file-organize