openspec-sync-specs

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the openspec CLI tool (e.g., openspec list --json) to retrieve and manage specification changes on the local system.\n- [PROMPT_INJECTION]: An indirect prompt injection surface exists because the agent processes and merges content from external delta specification files.\n
  • Ingestion points: The agent reads delta specs from openspec/changes/<name>/specs/*/spec.md and main specs from openspec/specs/<capability>/spec.md.\n
  • Boundary markers: The agent relies on standard Markdown headers (e.g., ## ADDED Requirements) for parsing, but there are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the requirement text.\n
  • Capability inventory: The agent has permissions to read, create, and modify markdown files within the openspec/ directory and execute the local openspec CLI tool.\n
  • Sanitization: No sanitization or data validation is performed on the content of the delta specs before it is merged into the main specification files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:52 PM