instagram-api

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). At runtime the required workflow uses a user-selected fetch_data call to https://instagram.fetcher.sh endpoints like /api/user/search and /api/post/.../comments, which ingest and return outsider-authored Instagram free text (bios, captions, comments) once the agent is pointed at an outsider-provided handle/hashtag/post/code.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill declares an MCP server at https://instagram.fetcher.sh/mcp and references runtime-generated machine-readable artifacts (https://instagram.fetcher.sh/openapi.json and https://instagram.fetcher.sh/llms.txt) that an MCP-connected agent can fetch at runtime to discover tools/endpoints and drive its prompts/actions.