coding-lifecycle
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a lifecycle that processes externally provided tasks and leverages the agent's code execution capabilities for verification, creating a standard attack surface for indirect prompt injection.
- Ingestion points: In SKILL.md, the agent is instructed to "Read the task or delegation request" to identify objectives and constraints.
- Boundary markers: There are no defined delimiters or instructions to ignore malicious commands that might be embedded within the external task descriptions.
- Capability inventory: The agent is directed to "Run quality checks" which include focused tests (such as
pytest), lint or type checks, and CLI checks as specified in SKILL.md and AGENTS.md. - Sanitization: The skill does not provide any mechanisms for sanitizing or validating the input from external tasks before the agent begins discovery, implementation, or verification steps.
Audit Metadata