rust-call-graph
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting untrusted data from the local workspace.
- Ingestion points: Function names, file paths, and symbol metadata retrieved via
LSPandReadtools from the project source code. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in function names or comments.
- Capability inventory: The skill is limited to
LSP,Read, andGlobtools. It lacks the ability to execute code, write to the filesystem, or perform network operations. - Sanitization: There is no evidence of sanitization or filtering of the symbol names retrieved from the LSP before they are presented to the agent for graph generation.
- [SAFE]: The
allowed-toolsconfiguration (LSP,Read,Glob) follows the principle of least privilege, restricting the skill to read-only analysis of the codebase.
Audit Metadata