symbol-table-builder
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a standard workflow for data organization in mathematical modeling. It reads local files like 'problem_parse.json' and 'qx_method_candidates.md' and writes to 'planning/symbol_table.md'.
- [DATA_EXPOSURE]: The skill accesses local workspace files for input data. No access to sensitive system paths (e.g., .ssh, .aws, .env) or hardcoded credentials was found.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data (problem parses and method candidates), it lacks any dangerous capabilities such as network access, command execution, or dynamic code evaluation. The risk of indirect prompt injection is negligible.
Audit Metadata