gsp-project-critique

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate design analysis tasks. It reads project files and generates critique documents using sub-agents. All file operations are restricted to the local project directory structure.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool for project state management and invoking phase transitions. No patterns of arbitrary command execution or privilege escalation were found.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted user data.\n
  • Ingestion points: Reads project design chunks, brand identity, and research recommendations in SKILL.md (Step 1).\n
  • Boundary markers: Content is inlined into agent prompts without explicit delimiters or warnings to ignore embedded instructions.\n
  • Capability inventory: Uses Bash, Write, Read, and Agent tools across the critique workflow.\n
  • Sanitization: No input validation or sanitization of ingested content is performed before interpolation into prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:01 AM