spec-inspect

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for local static analysis of specification files. It only accesses files within the '.specs/' subdirectory of a project, and its file operations are limited to reading Markdown documents and writing an inspection report and a handoff JSON. No attempts to access sensitive system files, environment variables, or credentials were identified.\n- [PROMPT_INJECTION]: The skill processes untrusted content from user-provided Markdown documents, which represents an indirect prompt injection surface. However, the potential impact is low due to the skill's restricted capabilities.\n
  • Ingestion points: requirement.md, design.md, and tasks.md within the project's .specs folder.\n
  • Boundary markers: Absent. The skill does not use specific delimiters to separate the content of the files from the agent's instructions.\n
  • Capability inventory: Tool access is limited to reading and writing local project files and using AskUserQuestion to suggest next steps. It cannot execute shell commands or make network requests.\n
  • Sanitization: No explicit sanitization or filtering of the file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:03 AM