php-expert
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a 'Memory Protocol' that instructs the agent to use the
Bashtool to read from a specific local file path (.claude/context/memory/learnings.md) and record new patterns. This is an intended feature for maintaining state across agent sessions. - [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and review user-provided PHP code, which represents an attack surface for indirect prompt injection.
- Ingestion points: Target files and paths provided by the user for code review and architectural guidance.
- Boundary markers: No specific boundary markers or 'ignore' instructions are defined in the prompt templates to isolate user data from system instructions.
- Capability inventory: The skill is granted access to powerful tools including
Bash,Write,Edit, andReadto perform its tasks. - Sanitization: The instructions do not specify any sanitization or validation of the untrusted code content before it is processed by the agent.
Audit Metadata