implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external specifications and tickets to guide its code implementation tasks.
- Ingestion points: External specifications and tickets describing the task graph (SKILL.md).
- Boundary markers: None identified. There are no instructions to use delimiters or ignore embedded instructions within the specs or tickets.
- Capability inventory: The skill manages subagents (exploration, implementer, merger), performs git operations (branching, worktrees, merging), writes files (markdown notes), and executes a code review tool (SKILL.md).
- Sanitization: None identified. There is no mention of escaping, validating, or filtering the external content before it is processed by the implementer subagents.
Audit Metadata