thermo-nuclear-review

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to utilize standard command-line interfaces for version control platforms.
  • Evidence: The instructions specify to "check the PR/MR discussion using gh/glab cli" to gather context from existing comments.
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data (code diffs and PR comments), which constitutes an indirect prompt injection attack surface.
  • Ingestion points: The agent reads code changes in the current branch and PR/MR discussion threads via CLI tools.
  • Boundary markers: The instructions do not define specific delimiters or isolation protocols to prevent the agent from accidentally executing instructions embedded within the code it is auditing.
  • Capability inventory: The skill has the capability to read local files and use network-enabled CLI tools (gh/glab).
  • Sanitization: No explicit sanitization or filtering of the audited code is requested in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:44 PM
Security Audit — agent-trust-hub — thermo-nuclear-review