The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses find, grep, and xargs in a Bash environment to identify and filter local files containing financial terminology. This is standard behavior for the skill's intended auditing function.
[PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection (Category 8).
Ingestion points: Local .md and .csv files are scanned and processed for financial data via find and grep commands in SKILL.md.
Boundary markers: No delimiters or 'ignore embedded instruction' warnings are used when processing content from these files.
Capability inventory: The skill utilizes Bash for file discovery and processing, Read for data ingestion, and AskUserQuestion for user interaction.
Sanitization: The skill lacks mechanisms to sanitize or validate the content of processed files before they are interpreted by the agent.

mint-unit