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
Bashtool 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, andAgenttools across the critique workflow.\n - Sanitization: No input validation or sanitization of ingested content is performed before interpolation into prompts.
Audit Metadata