ptlam-health-connector-code-style-dart

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard Dart and Melos commands to perform code analysis, formatting, and testing tasks. These commands include melos run format:dart:check, melos run analyze:dart:strict, melos run test:dart, and dart test. These operations are conducted within the local project environment using the repository's configured toolchain.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to process project-specific configuration and documentation files to guide the agent's behavior.
  • Ingestion points: The skill reads pubspec.yaml, pubspec.lock, analysis_options.yaml, AGENTS.md, and project source files (noted in SKILL.md and skills/ptlam-code-style-dart/SKILL.md).
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore potentially malicious embedded instructions within these repository files.
  • Capability inventory: The skill can execute shell commands via dart (analyze, test, format, pub, fix, doc) and melos (run) to manage the development lifecycle.
  • Sanitization: Absent. The skill treats the repository's configuration files as the source of truth for project conventions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 06:23 PM
Security Audit — agent-trust-hub — ptlam-health-connector-code-style-dart