job-description
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as old job descriptions and emails, which could potentially be used to inject instructions aimed at influencing the agent's behavior. This is a common characteristic of skills that process untrusted user input.\n
- Ingestion points: User-provided verbal hiring needs, legacy job descriptions, and request emails as described in the Workflow section.\n
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to separate user-provided data from its primary instructions.\n
- Capability inventory: The skill utilizes document creation tools to generate Word documents based on the provided input.\n
- Sanitization: The workflow does not specify any sanitization, filtering, or validation steps for the input text before it is formatted into the output.
Audit Metadata