The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill communicates with the remote vendor API at https://mcp.keyapi.ai to facilitate content discovery and retrieve engagement metrics. This connection is consistent with the skill's stated purpose and is documented in the setup instructions.\n- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and processes untrusted user-generated content (e.g., post captions, comments, and Reel descriptions) from Instagram.\n
Ingestion points: Untrusted content enters the agent's context through tools like get_post_comments, get_post_info, and get_posts_by_hashtag via the scripts/run.js utility.\n
Boundary markers: The skill instructions lack explicit boundary markers or instructions to the agent to disregard embedded commands in the retrieved content.\n
Capability inventory: The skill environment permits the agent to execute local scripts, perform network requests to the vendor server, and manage local file system access via a cache directory.\n
Sanitization: No sanitization or validation mechanisms are implemented to filter or escape the retrieved Instagram content before it is processed.

keyapi-instagram-content-discovery