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
openspecCLI 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
openspecCLI to manage the task implementation workflow.
Audit Metadata