multi-program-manager
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a structured guide for the AI to process affiliate marketing data. It performs calculations (such as Revenue Share and Earnings Per Click) and generates a strategic dashboard based on user input or previous conversation context.
- [PROMPT_INJECTION]: The skill processes external data via the 'programs' input schema, representing a potential surface for indirect prompt injection. However, the skill lacks any dangerous capabilities such as network access, file system modifications, or command execution that could be exploited through such an injection.
- Ingestion points: Data is ingested through the 'programs' list defined in the input schema in SKILL.md.
- Boundary markers: The skill relies on YAML structure for input/output but does not implement explicit boundary markers or 'ignore' instructions for the processed strings.
- Capability inventory: There are no subprocess calls, execution commands, network operations, or file-writing actions present in the skill.
- Sanitization: Input data is not explicitly sanitized or validated before being used in the analysis workflow.
Audit Metadata