sales-graphy

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill maintains a persistent knowledge mechanism through references/learnings.md. The agent is instructed to read from and append new information to this file, which creates a potential surface for indirect prompt injection if malicious data from a user session is processed and saved for future use.
  • Ingestion points: The skill reads references/learnings.md in Step 1 to gather context.
  • Boundary markers: There are no specific boundary markers or instructions to ignore embedded commands within the ingested text.
  • Capability inventory: The skill provides functional code templates and can route the agent to other domain-specific skills.
  • Sanitization: The instructions do not define any sanitization or validation logic for data appended to the learning file.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references an installation command npx skills add sales-skills/sales to add a related routing skill. This is a standard package installation from the skill's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 04:16 PM
Security Audit — agent-trust-hub — sales-graphy