openspec-bulk-archive-change

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands mkdir and mv to reorganize directories within the local openspec/ folder. The target paths are dynamically generated based on output from the openspec list command and user selection.\n- [PROMPT_INJECTION]: The skill implements an 'agentic' conflict resolution process that reads and interprets the content of local markdown files such as tasks.md and delta specs. This creates an indirect prompt injection surface where the content of these files could influence the agent's logic for merging specifications.\n
  • Ingestion points: Reads data from openspec/changes/<name>/tasks.md and the openspec/changes/<name>/specs/ directory.\n
  • Boundary markers: Absent. The agent is instructed to read files to 'understand' and 'determine resolution' without specific delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: Local filesystem manipulation via mkdir and mv, plus execution of the openspec CLI tool.\n
  • Sanitization: No specific sanitization or validation of the file content is performed before the agent processes the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:23 PM