symbol-table-builder
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the local workspace, reading specific project artifacts and writing a markdown documentation file. No suspicious patterns, network calls, or credential access were identified.
- [PROMPT_INJECTION]: The skill processes data from external files which could serve as a vector for indirect prompt injection.
- Ingestion points: Reads from
workspace/problem/problem-parser/problem_parse.jsonandmethods/Qx/qx_method_candidates.md. - Boundary markers: None explicitly defined for input data.
- Capability inventory: The skill writes to
planning/symbol_table.md. - Sanitization: No explicit sanitization of symbol names or descriptions.
Audit Metadata