aporia-persona-mapper

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements an interview-based workflow that processes untrusted user input to generate structured persona records.
  • Ingestion points: User responses provided during the Socratic interview stages (Steps 1 through 4) in SKILL.md.
  • Boundary markers: The skill explicitly requires the agent to synthesize the persona and obtain human confirmation (Step 5) before executing the final tool call.
  • Capability inventory: The skill uses the aporia:upsert_personas tool to write data to an external MCP server and aporia:fetch_personas to read existing data.
  • Sanitization: Instructions enforce strict validation against closed enum sets for fields such as role, painSeverity, and status, preventing arbitrary data injection into these fields.
  • [SAFE]: The skill uses specific MCP server tools (aporia:fetch_personas, aporia:upsert_personas) which are identified as vendor-internal resources belonging to the 'agentic-dev3o' ecosystem. These interactions are consistent with the skill's primary purpose and do not represent unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 06:23 AM
Security Audit — agent-trust-hub — aporia-persona-mapper