definition-of-done
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read and analyze potentially untrusted external data sources to verify task completion, which presents a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read user requests, repository-local instructions, specifications (PRD/spec/ARD), and issue descriptions in 'references/current-guidance.md'.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the external data being processed.
- Capability inventory: The checklist is used in contexts involving code commits, PR creation, and task reports, which interact with version control and terminal environments.
- Sanitization: There are no instructions for sanitizing or validating the content of the external documents before they are reviewed by the agent.
Audit Metadata