skills/braintrustdata/bt/bt-review/Gen Agent Trust Hub

bt-review

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically git diff main --name-only -- '*.rs', to identify changed files for targeted auditing. This is an expected and restricted use of command execution for a developer-oriented tool.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) because it ingests and processes untrusted data in the form of the codebase being audited.
  • Ingestion points: Reads source files including src/*.rs, src/args.rs, and src/main.rs (referenced in SKILL.md).
  • Boundary markers: None identified; the skill does not explicitly instruct the agent to ignore instructions embedded in the analyzed code.
  • Capability inventory: The agent can execute shell commands (git) and write findings to a local file (bt-review.md).
  • Sanitization: No evidence of sanitization or escaping of the ingested source code content before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references external guidelines from clig.dev, a well-known industry resource for CLI design. It does not perform any automated downloads from this service at runtime, instead relying on a local reference file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 09:50 PM