qe-iterative-loop
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing various development and quality assurance tools to achieve its goals. This includes running test frameworks (Jest, Vitest, Pytest), linting utilities, type checkers, and security auditing tools (
npm audit). It also interfaces with a specialized CLI toolset (aqe) for managing agent fleets and persistent memory storage. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from external tool outputs.
- Ingestion points: The skill instructions (in
SKILL.md) direct the agent to parse and analyze the stdout/stderr of test runs, coverage reports, and security scans. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are utilized when the agent interpolates external data into its reasoning loop.
- Capability inventory: The agent environment includes access to shell command execution (
npm,npx,aqe) and the capability to orchestrate additional agents via aTasktool. - Sanitization: There is no evidence of filtering, escaping, or validation being applied to the external data before it influences the agent's next iterative step.
Audit Metadata