openspec-propose
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the
openspecCLI tool, including creating new change directories (openspec new change), checking status (openspec status), and retrieving instructions (openspec instructions). These executions are core to the skill's intended functionality of managing specification-driven development workflows. - [DATA_EXPOSURE]: The skill reads project configuration and artifact instructions from the local environment via the CLI tool's JSON output. This data is used to populate documentation templates for 'proposal.md', 'design.md', and 'tasks.md'.
- [INDIRECT_PROMPT_INJECTION]: The skill processes instruction data retrieved from the CLI tool (
context,rules,template). While this data influences the agent's output generation, the skill includes explicit instructions for the agent to treat these as constraints rather than content to be copied directly, which helps mitigate accidental instruction following from the project configuration.
Audit Metadata