dal
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to clone the
data-access-layerrepository from the author's GitHub and install dependencies viapip. These are documented setup steps for the tool. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
dalCLI for operations like searching context, building graphs, and serving a local web interface. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided semantic files which presents an indirect prompt injection surface.
- Ingestion points: Files matching
semantic/*.yamlorsemantic/*.json. - Boundary markers: None explicitly defined in the instructions to prevent the agent from following instructions embedded in the metadata or descriptions within the ontology files.
- Capability inventory: Execution of the
dalCLI,git clone, andpip install. - Sanitization: No mention of validation or sanitization for the contents of the semantic files.
Audit Metadata