commission-calculator
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user input which is then interpolated into tool commands and reasoning steps.
- Ingestion points: The skill accepts user-defined program names, traffic data, and scenarios as defined in the Input Schema in SKILL.md.
- Boundary markers: The instructions do not define boundary markers or clear delimiters to separate user-provided data from system instructions, which could allow malicious instructions in the input to be followed by the agent.
- Capability inventory: The skill commands the agent to use the web_search tool to find pricing information and to interact with the openaffiliate.dev API.
- Sanitization: There are no instructions to sanitize or validate user-provided strings before they are used in search queries or decision-making logic.
Audit Metadata