The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to run mitmdump --set flow_detail=3 2>&1 | tee log.txt to capture network traffic. While this is a standard security testing practice aligned with the skill's purpose, users should be aware that traffic logs often contain sensitive data like credentials and personal information.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from log.txt to generate its report, creating a potential attack surface.
Ingestion points: The skill reads content from log.txt or results from previous skill executions to populate the report template.
Boundary markers: There are no instructions provided to the agent to delimit the untrusted log data or to ignore potential instructions embedded within those logs.
Capability inventory: The skill's primary function is generating formatted text (markdown/HTML/PDF). It does not exhibit dangerous capabilities like writing to system files or making unauthorized network requests in this file.
Sanitization: The skill does not implement sanitization or validation logic for the content found within the traffic logs before processing it.

mitm-report