objection-handler
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from prospect messages and user-provided facts to generate sales replies.\n
- Ingestion points: The skill prompts the user to paste external messages ("Their message with the objection") and facts ("Facts I can use to respond") directly into the prompt context in SKILL.md.\n
- Boundary markers: The skill uses labeled sections but lacks strong delimiters or specific instructions to ignore malicious directives embedded within the pasted content.\n
- Capability inventory: The skill's capabilities are limited to text generation; it does not perform file operations, network requests, or command execution.\n
- Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the model.
Audit Metadata