sales-merchant-of-record

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a persistent learning mechanism where the agent reads from and appends to references/learnings.md to accumulate knowledge.
  • Ingestion points: User input provided during the billing context assessment in SKILL.md Step 1.
  • Boundary markers: There are no instructions to the agent to treat data from the learnings.md file as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill instructions include routing logic to other tools and a command to install a related management skill using npx.
  • Sanitization: The skill lacks sanitization logic for user-provided data before it is persisted to the local filesystem.
  • [COMMAND_EXECUTION]: The skill documentation includes an installation command for a related utility: npx skills add sales-skills/sales --skill sales-do -a claude-code. This command downloads and executes a package from the vendor's repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 04:16 PM
Security Audit — agent-trust-hub — sales-merchant-of-record