The Agent Skills Directory

[PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill ingests data from external sources (Google Maps, Instagram, TikTok, Facebook, etc.) which are not under the user's or agent's control. Malicious instructions embedded in these external profiles or search results could potentially influence the agent's behavior during data processing or summarization.
Ingestion points: Data retrieved from various Apify Actors (e.g., instagram-scraper, tiktok-scraper, google-search-scraper) as described in SKILL.md.
Boundary markers: None identified in the provided workflow instructions.
Capability inventory: Execution of shell commands via mcpc and node (SKILL.md, Step 2 and Step 4); file system write access for saving CSV/JSON outputs (SKILL.md, Step 4).
Sanitization: No explicit sanitization or filtering of external content before processing is mentioned.
[COMMAND_EXECUTION]: The skill uses shell commands to interact with the Apify platform and run local scripts. This includes fetching Actor schemas via the mcpc tool and executing lead generation scripts using node. These are functional requirements for the skill's operation.
[EXTERNAL_DOWNLOADS]: The skill directs the user to install the @apify/mcpc package from the public npm registry. This tool is the official CLI for interacting with Apify's Model Context Protocol (MCP) server.

apify-lead-generation