stelow-product-pricing
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains a bash script block used to detect if the agent is in 'standalone' or 'workflow' mode by checking environment variables like $STELOW_WORKFLOW and $STELOW_STATE.
- [COMMAND_EXECUTION]: The workflow mode documentation describes a process where the system calls a local script located at
scripts/stelowto advance the state based on agent-generated outputs. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied data (such as product details and pricing questions) which creates a surface for indirect instructions.
- Ingestion points: The analytical framework processes user queries provided in the 'Example' section and uses them to generate recommendations.
- Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted user input from the skill's logic.
- Capability inventory: In its workflow mode, the skill provides data that influences the execution of a local script (
scripts/stelow) and coordinates with other skills in the pipeline. - Sanitization: There are no specified sanitization or validation steps for user-provided pricing data before it is interpolated into the workflow or output.
Audit Metadata