fiddler-traffic-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from captured HTTP traffic, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent ingests data from
LiveTrafficandAgentCallssession sources through tools likeGetSessionsandGetSessionDetailsas described inSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the processed traffic content.
- Capability inventory: The skill utilizes Fiddler Everywhere MCP tools to retrieve session lists and full request/reponse details, including headers and bodies.
- Sanitization: There are no instructions for sanitizing or filtering the captured HTTP content before it is processed by the agent's logic.
Audit Metadata