The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides examples of using curl to interact with the API. These are standard implementation examples for developers and do not involve unsanitized user input or privilege escalation.
[DATA_EXFILTRATION]: The skill performs network requests to api.scrapecreators.com and docs.scrapecreators.com. These are legitimate vendor domains required for the skill's core functionality of data scraping and fetching documentation.
[CREDENTIALS_UNSAFE]: The skill correctly instructs the use of an environment variable (SCRAPECREATORS_API_KEY) for API authentication, avoiding hardcoded secrets.
[PROMPT_INJECTION]: The skill processes data from external social media platforms, which constitutes an indirect prompt injection surface.
Ingestion points: Untrusted content from 27+ social media platforms (posts, comments, profiles) is ingested into the agent context via API calls.
Boundary markers: None explicitly defined in the instructions to separate API data from system prompts.
Capability inventory: The skill is permitted to use Bash, Read, Write, and WebFetch tools.
Sanitization: No specific sanitization or validation of external content is described before processing.

scrapecreators-api