rust-symbol-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted source code from the project workspace.
- Ingestion points: The skill uses
Glob("**/*.rs")to locate files and theReadandLSPtools to ingest content from project files (e.g.,src/lib.rs) into the agent's context. - Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the analyzed code, which is a standard surface for this category.
- Capability inventory: The skill is limited to
LSP,Read, andGloboperations. It lacks network access, file-write capabilities, or the ability to execute shell commands, significantly limiting the potential impact of an injection. - Sanitization: No explicit sanitization of the content returned by LSP or file reading is defined in the instructions.
Audit Metadata