implement-spec
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external data in the form of specifications and task tickets, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The workflow begins by reading specifications and tickets from external sources to define a task graph for implementation.
- Boundary markers: There are no instructions provided to treat the content of the specifications as data only or to ignore any embedded instructions that might attempt to hijack the subagents' behavior.
- Capability inventory: The skill orchestrates multiple subagents with capabilities to create git branches, manage pull requests, manipulate worktrees, and modify the codebase.
- Sanitization: The instructions do not include steps for sanitizing or validating the input specifications before they are passed to implementer subagents.
Audit Metadata