openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external project artifacts (e.g., specifications, design documents, and task lists) to guide the agent's implementation steps. This creates a surface for indirect prompt injection if these files contain malicious instructions.
  • Ingestion points: Content from files listed in the contextFiles metadata provided by the openspec instructions apply command.
  • Boundary markers: The skill does not explicitly define delimiters to separate input data from instructions, although it uses a structured loop for implementation.
  • Capability inventory: The skill is authorized to execute openspec CLI commands via Bash and perform file-system modifications for code implementation.
  • Sanitization: No specific text sanitization or filtering is applied to the ingested content.
  • [COMMAND_EXECUTION]: The skill is configured with a restricted toolset (Bash(openspec:*)), ensuring that the agent can only execute commands related to the OpenSpec ecosystem, which aligns with the principle of least privilege.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:18 PM
Security Audit — agent-trust-hub — openspec-apply-change