product-planning
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions, bypass attempts, or behavioral overrides were detected.
- [Data Exposure & Exfiltration] (SAFE): The skill accesses standard project artifacts (backlogs, roadmaps, personas). No access to sensitive system files, environment variables, or hardcoded credentials was found. No network exfiltration paths are present.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote scripts, external packages, or download-to-execution patterns are present.
- [Indirect Prompt Injection] (LOW): The skill is designed to process data from external files which acts as a vulnerability surface if those files contain untrusted content.
- Ingestion points:
PRODUCT_VISION.md,personas/PERSONAS.md,backlog/BACKLOG.md,roadmap/ROADMAP.md - Boundary markers: Absent; instructions do not explicitly tell the agent to ignore embedded commands in these files.
- Capability inventory: The skill is limited to reading and writing local text files; no shell execution or network capabilities were found.
- Sanitization: Absent; content from the files is used directly for drafting artifacts.
- [Dynamic Execution] (SAFE): No use of eval, exec, or runtime code generation.
Audit Metadata