skills/praveenperera/dotfiles/btx/Gen Agent Trust Hub

btx

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the btx CLI tool for managing and updating local copies of external repositories.
  • [EXTERNAL_DOWNLOADS]: The skill's primary function is to download code from external sources (such as GitHub) using HTTPS or SSH URLs.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface because it facilitates the ingestion and analysis of untrusted third-party codebases.
  • Ingestion points: Code from any user-provided repository URL is cloned to the local file system (SKILL.md).
  • Boundary markers: The skill does not define specific markers or instructions to help the agent ignore potential instructions embedded within the downloaded code.
  • Capability inventory: The workflow encourages the agent to use file exploration tools like Glob, Grep, and Read on the external content.
  • Sanitization: No sanitization or filtering logic is described for the content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 10:54 PM