openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill interpolates user-controlled change names into shell commands (e.g., openspec status --change "<name>"). This presents a command injection surface if the input contains shell metacharacters.\n
  • Ingestion points: User-provided or inferred change name.\n
  • Boundary markers: None.\n
  • Capability inventory: Shell execution and file operations.\n
  • Sanitization: No explicit sanitization mentioned.\n- [PROMPT_INJECTION]: The skill adopts "dynamic instructions" from the openspec CLI tool output, which could be used to influence agent behavior through indirect injection.\n
  • Ingestion points: CLI output from openspec instructions apply.\n
  • Boundary markers: None.\n
  • Capability inventory: Full task implementation loop (code changes, file writes).\n
  • Sanitization: Instructions are followed directly without validation.\n- [COMMAND_EXECUTION]: The skill frequently invokes the openspec CLI to manage the task implementation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:12 PM
Security Audit — agent-trust-hub — openspec-apply-change