openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected development tasks such as reading project files and executing a specific command-line interface tool (openspec) to track and implement changes. No suspicious code patterns or unauthorized access to sensitive data were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection because it processes untrusted data from external sources.
  • Ingestion points: The agent reads JSON output from the openspec CLI and content from project files defined as contextFiles in Step 4.
  • Boundary markers: Absent. No delimiters or specific instructions are provided to the agent to ignore potentially malicious instructions embedded in the external files it reads.
  • Capability inventory: The skill has the ability to execute shell commands (openspec) and perform arbitrary code modifications within the project directory.
  • Sanitization: Absent. The agent is instructed to parse output and implement changes based on natural language descriptions without any validation of the input source.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:38 AM
Security Audit — agent-trust-hub — openspec-apply-change