campaign-planner

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted user input into marketing templates.\n
  • Ingestion points: User-supplied parameters such as brand name, value propositions, and audience descriptions are used to fill out the campaign plan as described in SKILL.md.\n
  • Boundary markers: The templates in references/templates.md do not utilize delimiters or specific instructions to the agent to disregard potential instructions embedded within the user data.\n
  • Capability inventory: The skill utilizes file-writing capabilities to save plans to the memory/ directory and update memory/hot-cache.md, but lacks network access or code execution tools.\n
  • Sanitization: No input validation or sanitization routines are specified for the user-provided content.\n- [NO_CODE]: This skill consists entirely of Markdown instructions and reference templates. It does not include any Python scripts, Node.js code, or shell commands, which significantly limits the potential for traditional attack vectors like remote code execution or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:29 PM
Security Audit — agent-trust-hub — campaign-planner