skills/cogni-work/insight-wave/abm/Gen Agent Trust Hub

abm

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads project-specific configuration and customer data files (marketing-project.json, customers/*.json, content-strategy.json) to populate marketing templates. This access is necessary for the personalized nature of Account-Based Marketing (ABM) content and does not target system-sensitive files.
  • [EXTERNAL_DOWNLOADS]: Employs WebSearch and WebFetch to conduct research on target companies and stakeholders. These actions are triggered to find publicly available news, press releases, and LinkedIn profiles as part of the content generation workflow.
  • [COMMAND_EXECUTION]: While Bash is listed in the allowed-tools configuration, the provided workflow primarily uses high-level agentic tools for research and file manipulation. No direct shell command execution or persistence mechanisms were detected.
  • [PROMPT_INJECTION]: The skill maintains clear instructional boundaries and does not contain phrases attempting to override the agent's core safety guidelines or ignore previous instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:50 PM
Security Audit — agent-trust-hub — abm