research-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data which introduces a surface for indirect prompt injection attacks. \n
  • Ingestion points: The skill ingests transcripts, meeting notes, and customer research material from various sources (SKILL.md). \n
  • Boundary markers: There are no explicit boundary markers or instructions to disregard potential commands within the ingested text. \n
  • Capability inventory: The skill can write to the local filesystem (pm-workspace-docs/) and execute actions through multiple well-known MCP servers (Slack, HubSpot, Linear, Notion, PostHog). \n
  • Sanitization: No sanitization or validation logic is specified for the input data before it is processed or used in tool calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:31 PM