objection-handler
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its input mechanisms.
- Ingestion points: Processes user data from the 'Objection' and 'Context' inputs and retrieves local information from 'company-profile.md'.
- Boundary markers: The skill lacks delimiters or instructions to ignore instructions contained within the input data, making it possible for an attacker to influence agent behavior.
- Capability inventory: The skill is only capable of generating text; it does not have access to the network, the ability to write files, or the power to execute shell commands.
- Sanitization: There is no logic provided to sanitize or validate the input before it is included in the prompt context.
Audit Metadata