not-a-vibe-coder
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on reading eight project-specific markdown files (PRD, TechSpec, Schema, etc.) as its "persistent memory" to guide implementation. This creates a surface where an attacker could embed malicious instructions in these files to manipulate the agent's behavior during the build phase.
- Ingestion points: The skill reads PRD.md, TechSpec.md, AppFlow.md, Design.md, Schema.md, ImplementationPlan.md, Tracker.md, and Rules.md at the beginning of every session.
- Boundary markers: There are no instructions to use delimiters or ignore potentially malicious instructions embedded within these files.
- Capability inventory: The agent is instructed to perform autonomous file creation and project implementation (Phase 4) based on the contents of these documents.
- Sanitization: No sanitization or validation logic is defined for the content read from these planning files.
Audit Metadata