The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network operations to https://instagram.fetcher.sh. These calls are used to retrieve Instagram profile and content data as part of the skill's primary function. All requests use standard authentication patterns (Bearer tokens) and do not access or transmit sensitive local files.
[COMMAND_EXECUTION]: The skill documentation and scenario files (references/scenarios.md) provide curl command templates for the agent to use when interacting with the API. These are standard command-line tools for making HTTP requests.
[PROMPT_INJECTION]: The skill processes data from public Instagram sources, which presents a surface for indirect prompt injection attacks where malicious text in a bio or comment could attempt to influence agent behavior.
Ingestion points: All endpoints defined in references/endpoints.md that return user-generated content.
Boundary markers: None present in the instructions to separate untrusted data from the system prompt.
Capability inventory: Data is retrieved for use in the agent's conversational context; the skill does not grant the agent write access or additional system privileges.
Sanitization: No specific sanitization or content filtering is implemented within the skill definition.

instagram-scraper