The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash mkdir -p command to create the directory structure for saving generated Markdown files. This operation is driven by user input or a default path (~/Documents/research-memos/). While functional, execution of shell commands based on user-supplied variables presents a standard attack surface for command injection if the agent does not sanitize the input.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted user data for qualitative analysis.
Ingestion points: User-supplied coding snippets, categories, or raw research data segments defined as 'trigger content' in SKILL.md.
Boundary markers: Present. The skill instructions mandate wrapping the user's raw input within Markdown blockquotes (> ) in the final document to separate it from the AI-generated analysis.
Capability inventory: Capability to execute shell commands (mkdir) and perform local file system writes to save the generated memos.
Sanitization: Absent. There are no explicit instructions or regex patterns provided to sanitize the 'trigger content' or the user-provided file path before they are used in file system operations or included in the document.

analytic-memo