openspec-verify-change
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands using the
openspecCLI (list,status,instructions apply). These commands are used to retrieve metadata about project changes and identify the file paths of artifacts. - [INDIRECT_PROMPT_INJECTION]: The skill reads and parses text from project files, including
tasks.md,design.md, and specification files to extract requirements and verify implementation. - Ingestion points: Data is ingested from files listed in
contextFiles(returned byopenspec instructions apply) and from the local codebase through search operations. - Boundary markers: None identified; the instructions do not specify delimiters or warnings to ignore instructions embedded within the processed artifacts.
- Capability inventory: The skill has capabilities to read local files, execute specific CLI commands, and perform filesystem searches. It does not have network access or privilege escalation capabilities.
- Sanitization: The instructions do not specify sanitization or validation of the content read from files before it is processed by the agent.
Audit Metadata