rust-review

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several shell commands to manage the audit workflow, including mise run audit-extract, python3 docs/audit/extract.py, and mise run audit-serve. It also uses echo to append structured JSON data to reviews.jsonl and manages background processes for the audit dashboard.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from the local file system, including Rust source files, Markdown documentation, and JSONL audit logs. This data is used to drive the agent's analysis and output generation. While the skill has file-writing and command-execution capabilities, the risk is limited by the structured nature of the JSON output and the local scope of the operations within the graphrefly project context.
  • [EXTERNAL_DOWNLOADS]: The skill references the author's GitHub repository and the tomevault.io distribution platform for documentation and attribution. These are well-known resources within the context of the skill's authorship.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:21 AM
Security Audit — agent-trust-hub — rust-review