The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill contains a hardcoded API key (123456) in the SKILL.md file within the authentication header setup. Hardcoding credentials in source files is an insecure practice that can lead to unauthorized access.
[DATA_EXFILTRATION]: The skill communicates with an unverified external IP address (43.167.234.49) using curl to retrieve index and industry data. Interacting with non-domain-based infrastructure that is not a recognized or trusted service provider increases security risks.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the processing of untrusted data from an external API without safety controls.
Ingestion points: External data is ingested from API endpoints hosted at http://43.167.234.49:3101.
Boundary markers: No delimiters or instructions are used to separate API data from the agent's primary instructions.
Capability inventory: The skill uses curl to execute network operations.
Sanitization: There is no evidence of input validation or output sanitization for the data received from the remote server.

cn-index