rust-learner

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches information from well-known Rust ecosystem domains including doc.rust-lang.org, docs.rs, crates.io, and lib.rs.
  • [COMMAND_EXECUTION]: Utilizes the agent-browser CLI and mcp__actionbook__ tools to interact with web content and retrieve documentation.
  • [DATA_EXFILTRATION]: Performs network requests to well-known domains to retrieve Rust crate metadata and documentation.
  • [PROMPT_INJECTION]: Ingests untrusted data from external websites and processes it without explicit boundary markers, creating a surface for indirect prompt injection.
  • Ingestion points: Data from lib.rs, releases.rs, doc.rust-lang.org, docs.rs, and rust-lang.github.io.
  • Boundary markers: Absent.
  • Capability inventory: Bash, Task (subagents), Read, Glob, mcp__actionbook__.
  • Sanitization: No validation or sanitization of ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 11:44 AM