The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's setup instructions utilize python3 -c to extract configuration values from a JSON file using the Python standard library.
[DATA_EXFILTRATION]: The skill accesses ~/.gooseworks/credentials.json to retrieve API keys. This path is specific to the service's own configuration and is used for authenticating subsequent API requests.
[EXTERNAL_DOWNLOADS]: The documentation suggests the command npx gooseworks login, which facilitates the download and execution of the gooseworks utility from the npm registry.
[PROMPT_INJECTION]: The skill processes untrusted content from Instagram profiles and posts, creating an attack surface for indirect prompt injection.
Ingestion points: Instagram profile bios and post captions retrieved via shell-based API calls in SKILL.md.
Boundary markers: No explicit markers or delimiters are defined to separate the scraped data from agent instructions.
Capability inventory: The skill has access to shell execution via curl and python3 for its core functionality.
Sanitization: No sanitization or validation of the external Instagram data is described before it enters the agent's context.

instagram-scraper