implement-spec
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources, specifically specifications, issue tracker tickets, and research notes. This introduces an attack surface for indirect prompt injection where instructions hidden within these external documents could influence the agent's behavior.
- Ingestion points: The workflow involves reading specs, tickets, and research notes from an external issue tracker and shared directories (SKILL.md).
- Boundary markers: The instructions do not specify any boundary markers or special delimiters to separate the data being processed from the agent's own instructional context.
- Capability inventory: The skill allows the agent to create branches, manage git worktrees, perform merges, write files to the filesystem (via subagents), and invoke other tools such as
tddandcode-review(SKILL.md). - Sanitization: There is no evidence of input validation, filtering, or sanitization mechanisms for the external data before it is processed by the implementer subagents.
Audit Metadata