pub-package-explorer

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the dart pub unpack command to download and extract package archives from the official Dart repository at pub.dev.
  • [COMMAND_EXECUTION]: The workflow involves executing standard shell utilities, including jq, sed, find, ls, and rg, to parse project metadata and search through source code files.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external package code and local configuration files, creating a vulnerability where an agent could ingest untrusted data containing malicious instructions.
  • Ingestion points: Contents of .dart_tool/package_config.json and all source files within the unpacked package directory (e.g., lib/).
  • Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded in the external content.
  • Capability inventory: The skill allows filesystem reads (cat, rg), directory listing (ls, find), and downloading remote content via dart pub unpack.
  • Sanitization: No sanitization, validation, or filtering is performed on the downloaded content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 08:03 PM
Security Audit — agent-trust-hub — pub-package-explorer