multichannel-campaign-builder

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is composed of instructional markdown files that define a copywriting framework for outbound sales. It does not contain any executable scripts, shell commands, or configuration for external tools.\n- [NO_CODE]: There are no code files such as Python, JavaScript, or shell scripts associated with this skill, nor are there any remote dependencies or package installation commands. It operates purely as a set of logical instructions and templates for the agent to follow.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data provided by the user, such as product descriptions and persona details, which are then interpolated into generated outreach copy. While this provides a surface for indirect prompt injection, the skill lacks the system-level capabilities, such as file system access or network operations, necessary for an attacker to achieve an actionable exploit or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 10:21 AM
Security Audit — agent-trust-hub — multichannel-campaign-builder