principle-build-the-lever
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructions direct the agent to generate and run scripts, codemods, or generators to automate tasks. Evidence is found in the content of SKILL.md which outlines the principle of building repeatable artifacts.
- [INDIRECT_PROMPT_INJECTION]: The skill encourages the agent to process existing files and units of work to create automation tools, which introduces a surface where untrusted data could influence the generated logic.
- Ingestion points: Files and code units processed by the agent as described in SKILL.md.
- Boundary markers: None mentioned in the instructions.
- Capability inventory: File reading, script generation, and shell command execution.
- Sanitization: No sanitization or validation steps are defined for the input data.
Audit Metadata