the-objection-playbook
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads from
.agents/product-context.mdto retrieve product information and proof points. It implements a data protection mechanism where it explicitly instructs the agent to check a 'citability flag' and exclude internal-only figures from any generated prospect-facing content.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (product descriptions, personas, and competitors) to generate its output. While it lacks formal boundary delimiters for this input, the risk is negligible as the skill has no dangerous capabilities such as network access, file-writing, or code execution. Furthermore, it includes a comprehensive quality check phase to ensure generated claims trace back to the authoritative context file.
Audit Metadata