sales-objection
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses direct argument interpolation ($ARGUMENTS) to integrate user input into its operational workflow.
- Ingestion points: User input enters the context via the
$ARGUMENTSplaceholder inSKILL.mdandmeta.json(Step 2). - Boundary markers: There are no delimiters or instructions to ignore embedded commands within the user-provided arguments.
- Capability inventory: The skill is designed to read multiple local files, including
core/global-constraints.json,core/marketing-triggers.json, andbrand-voice.md. - Sanitization: The skill lacks logic to sanitize, escape, or validate the content of the
$ARGUMENTSbefore it is processed by the model, potentially allowing a user to influence the 'Logic Auditor' or bypass brand constraints.
Audit Metadata