The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files which is then used to construct LLM prompts.
Ingestion points: Values (such as company names) are read from input files like companies.csv (SKILL.md).
Boundary markers: Absent; input data is directly interpolated into the research query string without delimiters.
Capability inventory: The skill executes shell commands via subprocess.check_output to perform web research (SKILL.md).
Sanitization: No sanitization or validation is performed on input data before it is processed by the research tool.
[COMMAND_EXECUTION]: The skill uses Python's subprocess module to execute the tvly CLI tool with dynamically generated arguments based on file content.

fill-missing-fields