dag-dependency-resolver

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill has a vulnerability surface for indirect prompt injection as it processes external data and has filesystem modification capabilities.
  • Ingestion points: It uses Read and Glob tools to ingest DAG structure definitions and configuration data (SKILL.md).
  • Boundary markers: No boundary markers, delimiters, or explicit instructions are provided to help the agent distinguish between data and potentially embedded instructions within the files it processes.
  • Capability inventory: The skill is granted Write and Edit tools, allowing it to modify files on the system based on input that could be influenced by an attacker.
  • Sanitization: There is no evidence of input validation, schema enforcement, or escaping of content read from external files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 08:37 PM