implement-spec
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data in the form of specifications and tickets which drive the behavior of multiple subagents, creating a surface for instructions embedded in that data to influence the overall workflow.
- Ingestion points: The agent reads external 'spec and tickets' (SKILL.md) to construct a task graph.
- Boundary markers: There are no instructions provided to the agent to use delimiters or to treat the content of these external documents as untrusted data.
- Capability inventory: The agent and its subagents have the capability to create git branches, manage worktrees, perform merge operations, write markdown notes to local directories, and execute code reviews.
- Sanitization: The workflow does not include any steps for the validation, sanitization, or filtering of content extracted from tickets before it is used to direct implementation subagents.
Audit Metadata