The Agent Skills Directory

[COMMAND_EXECUTION]: The shell script scripts/smtp-connectivity-check.sh executes system utilities including dig and nc (netcat) to perform network diagnostics based on user-supplied domain inputs.
[DATA_EXFILTRATION]: The skill performs network operations to external hosts. The script scripts/smtp-connectivity-check.sh initiates TCP connectivity probes on port 25 to destination MX records, which are external, non-whitelisted targets.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could be leveraged for indirect injection attacks.
Ingestion points: scripts/analyze-postfix-log.py reads local log files provided as arguments; scripts/smtp-connectivity-check.sh ingests DNS MX records and implicitly processes SMTP banner responses.
Boundary markers: Absent; the scripts do not use specific delimiters or instructions to the agent to ignore potentially malicious content within the logs or network responses.
Capability inventory: The skill possesses the capability to read local files, execute shell commands, and perform network connectivity checks to arbitrary hosts.
Sanitization: scripts/analyze-postfix-log.py uses regular expressions to extract specific fields (status, relay), which provides basic structural validation but does not fully sanitize content for the LLM context.

smtp-production-debugging