The Agent Skills Directory

[SAFE]: The skill is a functional developer tool for traffic debugging. No malicious patterns, unauthorized exfiltration, or persistence mechanisms were detected. The skill correctly prioritizes authorized MCP tools over generic shell commands and directs users to proper setup procedures.
[PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it processes untrusted HTTP response bodies to perform its analysis.
Ingestion points: The GetSessionDetails tool in SKILL.md pulls full request and response content for analysis.
Boundary markers: There are no specific delimiters or "ignore embedded instructions" warnings provided for the data being analyzed.
Capability inventory: The skill is restricted to diagnostic analysis and reporting; it does not possess tools for file system modification, command execution, or external network exfiltration beyond its reporting purpose.
Sanitization: The skill instructions do not specify sanitization or escaping of the header or body content before the agent processes it for the final summary.

fiddler-traffic-debugging