rust-learner

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run the agent-browser CLI for web-based data retrieval.
  • Evidence: Instructions in the 'Inline Mode' section detail the use of agent-browser to open specific URLs and fetch text using selectors.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it ingests and processes data from external websites.
  • Ingestion points: The agent-browser and WebFetch tools are used to retrieve text from lib.rs, crates.io, docs.rs, and other Rust-related sites (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched content.
  • Capability inventory: The agent is granted capabilities including Bash (command execution), Task (subagent spawning), and Read (local file access).
  • Sanitization: There are no explicit instructions for sanitizing or validating the content retrieved from external sources before it is processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:57 AM
Security Audit — agent-trust-hub — rust-learner