openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various commands using the
openspecCLI tool, includingopenspec list,openspec status, andopenspec instructions, to retrieve project metadata and workflow state.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data to guide agent behavior. - Ingestion points: The agent parses JSON data from the
openspecCLI, specifically thecontext,rules,template, andinstructionfields. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the CLI-provided content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill has the capability to execute local CLI commands and perform file read/write operations on the local file system.
- Sanitization: There is no evidence of sanitization or validation performed on the strings retrieved from the CLI before they are used to influence file creation.
Audit Metadata