sales-miskmap

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's primary function is advisory, helping users navigate the MiskMap SaaS platform and its validation methodology.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes untrusted user-provided business ideas and description text.
  • Ingestion points: SKILL.md (Step 1) prompts for user business ideas and progress descriptions.
  • Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within user input.
  • Capability inventory: The skill instructs the agent to append new findings to references/learnings.md (Step 4), which is then read in subsequent sessions, creating a potential path for data poisoning.
  • Sanitization: No input validation or sanitization is performed on the user-provided data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 09:32 PM
Security Audit — agent-trust-hub — sales-miskmap