openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands like 'mkdir' and 'mv' to organize local project directories. Variables such as the change name are sourced from the output of the 'openspec' CLI or through direct user selection.
- [PROMPT_INJECTION]: The skill ingests and processes data from external sources, which constitutes an indirect prompt injection surface. 1. Ingestion points: Reads the content of the local 'tasks.md' file (Step 3) and parses JSON output from 'openspec list' and 'openspec status' commands (Steps 1 and 2). 2. Boundary markers: Absent; the skill does not use explicit delimiters or instructions to isolate the ingested data from the agent's core instructions. 3. Capability inventory: Ability to execute shell commands for file management and trigger the 'openspec-sync-specs' skill. 4. Sanitization: The skill performs targeted checks for checkbox markers in 'tasks.md' rather than ingesting and processing the file's text in its entirety.
Audit Metadata