Skills
skills/halo-dev/cli/openspec-archive-change/Gen Agent Trust Hub

openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to perform directory operations.
  • Evidence: Step 5 in SKILL.md uses mkdir -p openspec/changes/archive and mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name> to move files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files and CLI outputs which are subsequently used to drive logic and construct shell command arguments.
  • Ingestion points: SKILL.md reads content from tasks.md and processes JSON output from openspec list --json and openspec status --json.
  • Boundary markers: Absent. There are no delimiters or instructions provided to the agent to ignore potential instructions embedded within the ingested data.
  • Capability inventory: The skill can execute shell commands (mkdir, mv) and invoke the openspec CLI tool.
  • Sanitization: Absent. The <name> variable, which can be sourced from external CLI output, is interpolated directly into shell command strings in Step 5.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 06:46 AM