subagent-driven-development
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured workflow for implementation and code review using subagents. No malicious patterns, obfuscation, or unauthorized network operations were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external implementation plans which acts as an attack surface for indirect prompt injection.
- Ingestion points: The implementer subagent receives task text and context from an external plan via
SKILL.mdandimplementer-prompt.md. - Boundary markers: The skill uses text placeholders like
[PASTE FULL TASK TEXT]to delimit data, though no explicit safety instructions are included in the sub-prompts to ignore embedded instructions. - Capability inventory: The skill allows subagents to modify the file system and run verification checks.
- Sanitization: No explicit sanitization or filtering of the ingested plan content is specified.
Audit Metadata