superspec-research

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill performs multiple calls to a local CLI tool named openspec. These calls are structured and used to list, create, and inspect status of change requests. While this involves command execution, it is limited to a specific tool required for the skill's functionality.- [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface (Category 8) by ingesting and acting upon instructions or templates returned by the openspec tool.
  • Ingestion points: Data enters the agent context through the stdout of openspec status and openspec instructions commands.
  • Boundary markers: No explicit delimiters or warnings are used to differentiate tool-provided content from system instructions.
  • Capability inventory: The agent has the capability to write files to the local filesystem (e.g., proposal.md, specs/**/*.md).
  • Sanitization: There is no evidence of sanitization or validation of the content received from the CLI tool before it is used to drive file-writing operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:32 PM