runtime-performance-auditor

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code from the lib/ directory and configuration from pubspec.yaml to perform its audit. Because it reads external files without enforcing clear boundary markers or sanitization, it possesses a surface for indirect prompt injection.
  • Ingestion points: Dart source files within the lib/ directory and the pubspec.yaml file are processed using grep and file-reading tools (SKILL.md).
  • Boundary markers: There are no defined delimiters or specific instructions for the agent to ignore or isolate embedded instructions found within the analyzed codebase.
  • Capability inventory: The skill has the capability to run local shell commands (grep, wc) and read files, but it lacks network access or file-write permissions.
  • Sanitization: No sanitization, escaping, or structural validation is applied to the ingested content before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:24 PM
Security Audit — agent-trust-hub — runtime-performance-auditor