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
aqeCLI 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
aqeCLI 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