The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to run the mcpc CLI and a local Node.js script (run_actor.js). These commands are used to fetch Actor schemas and perform data scraping tasks.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @apify/mcpc package from the npm registry and communicates with official Apify API endpoints (api.apify.com) to run actors and download datasets.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
Ingestion points: External data (reviews, ratings, comments) is ingested from various platforms via Apify Actors and processed in run_actor.js.
Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the scraped content.
Capability inventory: The skill has the ability to execute shell commands (node, mcpc) and write files to the local filesystem via writeFileSync.
Sanitization: While the skill provides protection against CSV formula injection in the csvCell function, it does not sanitize content before displaying it in the agent's chat context, allowing potentially malicious instructions in scraped data to influence the agent.

apify-brand-reputation-monitoring