linkedin-campaign-complete

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of Markdown files (SKILL.md and references/templates.md). There are no associated scripts (.py, .js, .sh), binaries, or configuration files that could execute code or perform actions on a system.
  • DATA_EXFILTRATION (SAFE): There are no network-related commands (curl, wget) or sensitive file path references. The skill does not possess the capability to access or transmit data.
  • PROMPT_INJECTION (SAFE): The example prompts and instructions are standard educational content for an AI agent. There are no patterns suggesting attempts to bypass safety filters or extract system instructions.
  • INDIRECT PROMPT INJECTION (INFO): While the skill suggests processing external data (LinkedIn profiles, post engagement), it lacks any 'write' or 'execute' capabilities. The risk is negligible as it only provides a framework for generating text within the agent's reasoning space.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 12:30 PM