openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the external
openspecCLI to perform its functions. It executes several commands includingopenspec list,openspec status, andopenspec instructionsto manage the lifecycle of project artifacts. - [INDIRECT_PROMPT_INJECTION]: The skill features a vulnerability surface where it ingests untrusted data from external files and CLI outputs to influence its generation of new files.
- Ingestion points: The agent is instructed to read dependency files (completed artifacts) and parse instructions provided by the
openspecCLI. - Boundary markers: While the skill instructs the agent not to copy context/rules blocks directly into the output, there are no specific delimiters or instructions to ignore potential adversarial commands embedded within the data files themselves.
- Capability inventory: The skill possesses the capability to execute shell commands (via the CLI) and perform file system read and write operations.
- Sanitization: The instructions do not define any sanitization or validation steps for the content retrieved from the external dependencies.
Audit Metadata