The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted users via Instagram Direct Messages.
Ingestion points: External content is pulled into the agent's context using the instagram-cli read and instagram-cli inbox commands described in SKILL.md.
Boundary markers: The instructions recommend using --output json which provides structural delimiters, but the skill does not define semantic boundaries or warnings to ignore instructions within the message body.
Capability inventory: The skill grants the agent capabilities to write to the local file system (using --download and --file) and to send messages (using send and reply) as evidenced in SKILL.md.
Sanitization: The skill does not provide any mechanisms or instructions for sanitizing, validating, or filtering the content of incoming messages.
[COMMAND_EXECUTION]: The skill functions by executing various subcommands of the instagram-cli utility to perform its tasks.

instagram-skill