openspec-apply-change

Warn

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs and executes shell commands using input provided by the user, specifically the <name> variable in commands like openspec status --change "<name>" --json. This presents a command injection risk if the user input contains shell metacharacters (e.g., quotes, semicolons, or pipes) that the agent's execution environment does not properly escape.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and acts upon content from external files (retrieved via contextFiles) without any sanitization or boundary markers to distinguish between data and instructions.
  • Ingestion points: The agent reads all file paths listed in the contextFiles output of the openspec instructions apply command (SKILL.md, Step 4).
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions or prompts found within the processed files.
  • Capability inventory: The agent has the capability to execute shell commands via the openspec CLI and perform unrestricted file modifications in the local workspace.
  • Sanitization: Absent. The skill provides no mechanism to validate, escape, or filter the content of the tasks or files before the agent implements the described changes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 12, 2026, 11:12 AM
Security Audit — agent-trust-hub — openspec-apply-change