create-durable-plan
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from the current conversation and write it to the local filesystem in the
docs/plansfolder. - Ingestion points: Instructions specify using the "current conversation's plan" as the source of data (SKILL.md).
- Boundary markers: There are no instructions defining delimiters or warnings to ignore embedded instructions within the ingested plan data.
- Capability inventory: The skill has file-writing capabilities to create folders and files within the project structure (SKILL.md).
- Sanitization: The skill lacks instructions for sanitizing, escaping, or validating the content of the plans before they are persisted to the disk.
Audit Metadata