openspec-proposal-creation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands for file system operations, including find, grep, mkdir, ls, and test. These are employed to scaffold directory structures, search existing requirement files, and perform validation of the generated proposal files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from existing specification files in the spec directory to inform the creation of new proposals.
- Ingestion points: Files located in spec/specs/ are read during the initial review phase of the workflow.
- Boundary markers: The instructions do not specify the use of delimiters or ignore instructions for the ingested content.
- Capability inventory: The skill has the ability to read from the filesystem and write to specific directories using shell commands.
- Sanitization: There are no explicit sanitization or validation steps for the content read from external specification files.
Audit Metadata