exec
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to facilitate the execution of shell commands. Specifically, the lev exec tool is used with a --verifier flag that accepts arbitrary shell commands for task validation. Additionally, the skill is instructed to run commands and flows defined in project-specific configuration files such as execution.yaml.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads and acts upon external project files to determine execution logic.\n
- Ingestion points: The skill reads Project Context, execution.yaml, dna.yaml, and other task-related project artifacts from the filesystem.\n
- Boundary markers: There are no explicit instructions to use delimiters or specific ignore embedded instructions warnings within the data processed from these files.\n
- Capability inventory: The skill allows for arbitrary shell command execution (via verifiers and lev flows) and file system interactions for reconciliation.\n
- Sanitization: The skill specifies a lev task validate step to check tasks before dispatching execution, which acts as a validation check for the ingested data.
Audit Metadata