openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the openspec CLI to perform project management tasks including listing changes, checking status, and syncing specifications.
  • [COMMAND_EXECUTION]: Uses standard shell commands such as mkdir and mv to organize local project files and move completed work to an archive directory.
  • [PROMPT_INJECTION]: Flags a surface for indirect prompt injection as the skill processes content from tasks.md and CLI JSON outputs which could be influenced by external actors. * Ingestion points: Reads data from tasks.md and outputs from openspec list/status commands. * Boundary markers: Does not use specific delimiters or instructions to prevent the agent from following commands embedded within the ingested data. * Capability inventory: Includes the ability to execute shell commands and call sub-agents via the Task tool. * Sanitization: No explicit content validation or sanitization is performed on the ingested task descriptions or status reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 01:57 AM