openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources including openspec CLI outputs and a local tasks.md file.
  • Ingestion points: Reads openspec list --json (Step 1), openspec status --json (Step 2), tasks.md (Step 3), and delta specifications at openspec/changes/<name>/specs/ (Step 4).
  • Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when processing this content.
  • Capability inventory: The skill can create directories (mkdir), move files (mv), and invoke other agent skills via the Task tool.
  • Sanitization: There is no explicit sanitization or validation of the content read from tasks.md or the delta specs before they are summarized or passed to sub-agents.
  • [COMMAND_EXECUTION]: The skill executes shell commands for file system operations.
  • Evidence: Uses mkdir -p openspec/changes/archive and mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>. While these are standard for archiving, the <name> variable is derived from tool output or user selection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 04:01 AM
Security Audit — agent-trust-hub — openspec-archive-change