qe-code-intelligence

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the aqe CLI tool to perform codebase indexing, semantic search, dependency mapping, and complexity analysis. This execution of CLI commands is a core component of the skill's stated purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase data to build knowledge graphs, creating a surface for potential indirect prompt injection.\n
  • Ingestion points: Source code files within the src/ directory are read and indexed during knowledge graph construction as described in the activation and workflow sections of SKILL.md.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are specified for the processed codebase content.\n
  • Capability inventory: The skill enables shell command execution via the aqe CLI and has read access to local files for analysis.\n
  • Sanitization: No sanitization, validation, or filtering of the source code content is specified prior to it being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:16 PM
Security Audit — agent-trust-hub — qe-code-intelligence