skills/garethmanning/education-agent-skills/cross-cultural-task-validity-checker/Gen Agent Trust Hub
cross-cultural-task-validity-checker
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via multiple input fields and interpolates it into the system prompt.\n
- Ingestion points: Fields
task_or_practice,intended_context,source_context,student_level,subject_area, andspecific_concernsdefined inSKILL.mdreceive external data.\n - Boundary markers: The prompt lacks specific delimiters (such as triple backticks or unique tokens) to isolate user-supplied content from internal instructions.\n
- Capability inventory: The skill has no associated tools, file system access, network capabilities, or code execution functions. It is purely text-generative.\n
- Sanitization: No input validation or sanitization is performed on the provided strings.\n- [NO_CODE]: The skill consists solely of instructions and metadata, with no included scripts, binaries, or automated tasks.\n- [SAFE]: No malicious patterns, hidden commands, or risky behaviors were identified during the analysis.
Audit Metadata