The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill scrapes and processes untrusted data from Instagram, including user biographies and post text. This data is returned to the agent context, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Instagram profile metadata (username, biography) and post-level metrics retrieved from the Apify dataset in SKILL.md.
Boundary markers: The skill does not define specific boundary markers or instructions for the agent to ignore or sanitize instructions found within the scraped data.
Capability inventory: The skill utilizes shell execution for node scripts and curl commands, along with local file system writing for dataset exports.
Sanitization: There is no evidence of sanitization or filtering of the external content before it is displayed or saved.
[EXTERNAL_DOWNLOADS]: The skill interacts with the Apify API (api.apify.com) to execute scraping tasks and retrieve results. This involves network requests to a well-known service and the use of an APIFY_TOKEN for authentication. The skill correctly recommends managing this token via environment variables or .env files.
[DYNAMIC_EXECUTION]: The skill supports a customMapFunction parameter, which accepts a JavaScript string to transform output objects. While this execution is performed on the remote Apify platform rather than the local agent environment, the pattern allows for the transmission and execution of user-defined code logic.

scraping-instagram-profile-data