The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with the Instagram Graph API (graph.facebook.com) for media retrieval, hashtag searches, and content publishing.
[COMMAND_EXECUTION]: References a vendor-specific diagnostic tool zero doctor used to validate connection parameters and environment variables.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it instructs the agent to fetch and handle untrusted content from the Instagram platform.
Ingestion points: API response fields such as caption and recent_media described in Section 1 and Section 3.2 of SKILL.md.
Boundary markers: No markers are defined to isolate retrieved data from the agent's instructions.
Capability inventory: The skill utilizes shell execution via curl and can write temporary JSON data to /tmp/request.json.
Sanitization: No specific filtering or sanitization of the external API content is implemented before processing.

instagram