openspec-sync-specs

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local command-line tool openspec list --json to retrieve available changes for user selection. This is a standard integration for the described workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown content from 'delta spec' files (openspec/changes/<name>/specs/*/spec.md) to guide its file modification logic. Because the agent must 'intelligently' interpret the content of these files to apply changes, there is a potential surface for instructions embedded within the specifications to influence the agent's behavior.
  • Ingestion points: Reads delta spec files from the local filesystem.
  • Boundary markers: None explicitly defined to separate data from instructions during the interpretation phase.
  • Capability inventory: Performs file read and write operations on the local filesystem (openspec/specs/).
  • Sanitization: None described for the content being merged into the main specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 02:17 PM