implement-spec
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external specifications and tickets, which are untrusted data sources.
- Ingestion points: The instructions in
SKILL.mdrequire the agent to read and understand external specifications and task tickets to build a task graph. - Boundary markers: The instructions lack explicit delimiters or safety markers to differentiate the data in the specifications from the agent's operational logic.
- Capability inventory: The skill coordinates subagents with capabilities to write files (exploration notes), manage worktrees, create branches, and merge code.
- Sanitization: There is no requirement or mechanism mentioned for sanitizing or validating the content of the external specifications before they are used to drive subagent actions.
Audit Metadata