openspec-archive-change

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands (mkdir and mv) with variable interpolation for change names and dates. If these variables contain shell metacharacters, it could lead to command injection if the underlying agent does not properly escape inputs.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting and processing content from external sources.\n
  • Ingestion points: The skill reads the tasks.md file and processes JSON output from the openspec CLI tools.\n
  • Boundary markers: Absent. There are no specific delimiters or instructions for the agent to ignore potentially malicious content within the ingested files.\n
  • Capability inventory: The skill has the ability to execute filesystem operations (mkdir, mv) and run CLI tools.\n
  • Sanitization: Absent. The skill does not describe any validation or sanitization steps for the data retrieved from tasks.md or CLI outputs before displaying summaries or warnings.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:23 PM