The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the instagram-pp-cli and instagram-pp-mcp tools from the vendor's repository (github.com/mvanhorn/printing-press-library) and NPM registry (@mvanhorn/printing-press-library).
[COMMAND_EXECUTION]: The primary function of the skill involves executing the instagram-pp-cli binary to perform analytics tasks such as account comparison, follower growth tracking, and media performance analysis.
[DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> flag and an optional feedback mechanism (INSTAGRAM_FEEDBACK_ENDPOINT) that allow the transmission of data to external endpoints.
[PROMPT_INJECTION]: The skill processes untrusted data from the Instagram Graph API, which presents a surface for indirect prompt injection.
Ingestion points: Data retrieved from Instagram Business/Creator accounts, including media captions, comments, and competitor profiles processed by the CLI tool.
Boundary markers: The skill instructions do not define any delimiters or warnings for the agent to ignore instructions embedded in the ingested data.
Capability inventory: The skill has access to shell execution via the CLI, file writing through the --deliver flag, and network operations for API requests and webhooks.
Sanitization: There is no documentation or evidence of sanitization or filtering applied to the external content before it is processed by the agent.

pp-instagram