convex-development-general

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file includes a 'Memory Protocol' instructing the agent to run the cat command on .claude/context/memory/learnings.md. While intended for context persistence, instructing an agent to execute shell commands directly creates a potential vector for unintended operations.
  • [PROMPT_INJECTION]: The process of reading the learnings.md file constitutes an indirect prompt injection surface.
  • Ingestion points: The agent is instructed to read content from .claude/context/memory/learnings.md at the start of its task.
  • Boundary markers: No delimiters or 'ignore instructions' warnings are present around the ingested content.
  • Capability inventory: The agent has access to Read, Write, and Edit tools.
  • Sanitization: No sanitization or validation of the file content is performed before the agent reads it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 11:41 AM