skills/badlogic/pi-skills/vscode/Gen Agent Trust Hub

vscode

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing the code and git command-line tools.
  • Commands: code -d, git show, and git log are used to facilitate file diffing and version comparison.
  • Usage: Temporary files are created in /tmp to store staged or historical versions of files for comparison.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles file paths and git revision hashes provided by the user or agent, representing a potential attack surface for malformed inputs.
  • Ingestion points: File paths and commit identifiers are interpolated into shell commands in SKILL.md.
  • Boundary markers: None are explicitly defined for these inputs.
  • Capability inventory: The skill is scoped to file system read access via git and opening a GUI editor via code.
  • Sanitization: No specific sanitization or validation of the input strings is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:14 PM