openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads 'tasks.md' to determine if tasks are complete (Step 3). This file is an untrusted ingestion point that could be leveraged for indirect prompt injection. * Ingestion points: 'tasks.md' referenced in the archival steps. * Boundary markers: None present. * Capability inventory: File system manipulation ('mkdir', 'mv') and 'openspec' CLI execution. * Sanitization: None provided.
  • [COMMAND_EXECUTION]: The skill executes shell commands for file management tasks like creating archive directories and moving folders, and it uses the 'openspec' CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 08:39 AM