competitive-intel

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of natural language instructions and templates for the AI agent to follow. It does not contain executable code, scripts, or binary files.
  • [DATA_EXPOSURE]: The skill references a local file path .agents/sales-context.md to gather business context. This is a standard practice for agent-based skills to maintain context and does not involve accessing sensitive system files or credentials.
  • [PROMPT_INJECTION]: While the skill uses persona-defining instructions ('You are a B2B sales strategist'), it does not attempt to override safety guidelines, bypass constraints, or ignore previous system instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it processes data from user responses and a local markdown file. However, because the skill has no high-risk capabilities (such as network access, file writing, or command execution), this surface does not pose a significant security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 10:09 AM
Security Audit — agent-trust-hub — competitive-intel