impact-check
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by reading and searching the entire codebase to identify symbol references.
- Ingestion points: The skill searches all files (e.g.,
*.ts) and reads content to identify imports, calls, and references (Step W02, RULE-02). - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions that might be embedded in the analyzed code files.
- Capability inventory: The skill has capabilities to read the entire codebase and write to specific local paths (
llmwiki/wiki/sources/draft/,llmwiki/wiki/index.md,llmwiki/wiki/log.md). - Sanitization: No sanitization or escaping mechanisms are described for the content extracted from the codebase before it is interpolated into the output report or wiki entries.
Audit Metadata