The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions involve executing local scripts (node scripts/run-state-check.js and bash scripts/evidence-log.sh) to maintain the research state and log quotes to the repository root. These are intended functions for managing collected data.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external market research sources.
Ingestion points: The agent is instructed to search for and capture quotes from external sources and URLs.
Boundary markers: The instructions do not define specific delimiters for separating processed quotes from the system prompt.
Capability inventory: The skill has the capability to run local shell scripts and node processes.
Sanitization: No explicit sanitization or escaping mechanisms for the captured quotes are defined in the instructions.

market-research