tenzir-create-parser-package
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's operations, including file creation and code generation, are entirely consistent with its stated purpose of assisting developers with Tenzir package creation.
- [PROMPT_INJECTION]: The skill's surface for indirect prompt injection was evaluated because it processes log samples to generate code.
- Ingestion points: Log samples provided by the user and documentation/samples retrieved from web searches (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters to separate data from instructions within the log samples.
- Capability inventory: Scaffolding directories and writing manifests/scripts using the agent's file system tools.
- Sanitization: The agent translates data into TQL code based on structural patterns, which minimizes the risk of executing embedded instructions as commands.
Audit Metadata