The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from various external sources (e.g., Google Maps, Facebook, TripAdvisor) which may contain content controlled by third parties. This creates a surface for indirect prompt injection when the agent is asked to summarize the findings.
Ingestion points: Market data is fetched from Apify datasets via the run_actor.js script.
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore potentially malicious content within the fetched data.
Capability inventory: The skill utilizes file system access (writeFileSync) and network requests (fetch) through its runner script.
Sanitization: The run_actor.js script includes logic to sanitize CSV outputs by prepending a single quote to cells starting with injection-prone characters (=, +, @, -), reducing the risk of spreadsheet-based attacks.
[COMMAND_EXECUTION]: The workflow requires the execution of shell commands, specifically the mcpc CLI tool and a local Node.js script. These are used to dynamically fetch actor schemas and execute market research tasks.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @apify/mcpc package from the official NPM registry. This is a recognized tool from a well-known service provider relevant to the skill's primary function.

apify-market-research