openspec-sync-specs

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the openspec CLI tool to list, status, and manage specification stores. This execution is performed via a Bash tool and is limited to the openspec command set as defined in the skill's allowed tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external markdown files (delta specs) to guide its file-editing behavior.
  • Ingestion points: Delta specification files identified by the openspec status command, typically located within the project's specs/ directory.
  • Boundary markers: The instructions direct the agent to identify specific markdown headers (e.g., ## ADDED Requirements) to parse data, but there are no explicit delimiters or instructions to ignore potential natural language commands embedded within those sections.
  • Capability inventory: The agent is authorized to read local files, modify/write local markdown files, and execute openspec CLI commands via Bash.
  • Sanitization: The skill lacks explicit sanitization or validation logic for the content read from delta specs before it is merged into the main specification files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 09:23 AM