stelow-product-trust-building
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute local shell scripts to manage and advance the workflow state.
- Evidence: The documentation instructs the agent to run
scripts/stelow nextto determine the next stage andscripts/stelow advance <next-candidate>to update the system state. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external descriptions of business problems to generate trust-building strategies, creating a surface where untrusted data could influence agent behavior.
- Ingestion points: User-provided business context and challenge descriptions (e.g., "Checkout abandonment is 70%") in the SKILL.md examples.
- Boundary markers: None present; the examples do not show delimiters or instructions to ignore embedded commands within the input data.
- Capability inventory: Local command execution via the
scripts/stelowutility. - Sanitization: No sanitization or validation logic is specified for the input data before it is processed by the agent.
Audit Metadata