objection-handling
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and does not contain any executable scripts, command-line operations, or remote dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied objection text and email content. While this creates a standard ingestion surface for untrusted data, the skill lacks capabilities to perform file writes or network operations, preventing exploitation.
- Ingestion points: User-provided objection descriptions and email content (SKILL.md).
- Boundary markers: None.
- Capability inventory: The skill instructions check for and read a local context file (.agents/sales-context.md) but contain no file-write, network, or command execution capabilities (SKILL.md).
- Sanitization: None.
Audit Metadata