ddd-context
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, hidden commands, or security vulnerabilities were detected in the skill instructions or configurations.
- [PROMPT_INJECTION]: Evaluated the surface for indirect prompt injection. 1. Ingestion points: The context name is ingested via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: No delimiters or boundary markers are used for the context name input. 3. Capability inventory: The skill utilizes Bash(mkdir) for directory creation and the Write tool for file generation within the local file system. 4. Sanitization: The skill explicitly includes a validation instruction ('Validate name: Ensure the context name is kebab-case') which acts as a safeguard against malicious input that could lead to directory traversal or command injection.
Audit Metadata