openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external context and guidance via 'openspec instructions' commands. This creates a surface where external data can influence the agent's behavior during the archiving process. 1. Ingestion points: The skill reads JSON output from 'openspec instructions archive' and 'openspec instructions specs'. 2. Boundary markers: Instructions explicitly tell the agent to treat these inputs as advisory, separate them from core CLI logic, and report conflicts. 3. Capability inventory: The skill utilizes 'Bash(openspec:*)', 'mkdir', and 'mv'. 4. Sanitization: The agent is instructed not to copy external text verbatim and to prioritize user choices over conflicting guidance.
- [COMMAND_EXECUTION]: The skill executes local shell commands using the 'openspec' CLI, as well as 'mkdir' and 'mv', to organize files into an archive directory. These operations are within the expected scope of a change management tool.
Audit Metadata