openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including CLI JSON outputs and local dependency files. It mitigates potential injection risks by providing explicit guardrails that instruct the agent to treat these inputs as internal constraints only, rather than content to be reproduced in the output files.
- [COMMAND_EXECUTION]: The skill relies on the
openspecCLI to perform its functions (openspec list,openspec status,openspec instructions). These commands are used to retrieve structured data about the current project state and are consistent with the skill's stated purpose. - [SAFE]: No obfuscation, data exfiltration, or unauthorized persistence mechanisms were found. The skill uses standard interactive patterns (AskUserQuestion) to ensure user control over significant actions like change selection.
Audit Metadata