The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from Instagram, including profile bios, post captions, video transcripts, and user comments, which could contain instructions meant to influence the agent's behavior.
Ingestion points: Data is retrieved via instagram comments, instagram transcript, instagram profiles get, and instagram posts as described in SKILL.md and references/instagram-command-map.md.
Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between retrieved data and control instructions.
Capability inventory: The skill uses the scrapesocial CLI tool for research and data retrieval tasks.
Sanitization: There is no evidence of sanitization or filtering applied to the external Instagram content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the scrapesocial package from the NPM registry. This is an external dependency necessary for the skill's core functionality.

scrapesocial-instagram