The Agent Skills Directory

[COMMAND_EXECUTION]: Uses openssl and curl to interact with remote servers for SSL/TLS inspection. These operations are consistent with the skill's stated purpose of checking certificate validity and protocol support.\n- [COMMAND_EXECUTION]: Interpolates input variables HOST and PORT into shell command strings. This is a common pattern in CLI-based skills but presents a surface for command injection if the input provided to the agent is not properly sanitized.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes raw output from remote servers via openssl and curl.\n
Ingestion points: Output from openssl s_client and curl -sv (SKILL.md).\n
Boundary markers: No delimiters or safety instructions are used to isolate the server output from the agent's context.\n
Capability inventory: Shell execution and network access (SKILL.md).\n
Sanitization: No escaping or filtering is applied to the data retrieved from the remote host before the agent processes it.

ssl-check