openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspec list --jsoncommand to retrieve a list of available changes.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.\n - Ingestion points: Reads delta specification files from the local file system at
openspec/changes/<name>/specs/*/spec.md.\n - Boundary markers: Absent; the instructions do not define delimiters to separate file content from agent instructions.\n
- Capability inventory: The agent is authorized to read and write markdown files in the
openspec/specs/andopenspec/changes/directories.\n - Sanitization: Absent; the skill requires the agent to interpret natural language intent from the delta specs to intelligently modify main specifications.
Audit Metadata