codeigniter-knowledge
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill functions as a static knowledge base and set of diagnostic tools for PHP development. It does not include any code for execution, remote downloads from untrusted sources, or attempts to exfiltrate data.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by defining patterns for the agent to ingest and process untrusted external data (the user's source code) during auditing. This is documented as the primary utility of the skill for performing static analysis, and the risk is mitigated by the highly specific nature of the search patterns provided.
- [COMMAND_EXECUTION]: The documentation includes multiple shell command templates (e.g.,
GrepandGlobpatterns) designed for auditing local projects. These commands are benign and standard for codebase discovery and architectural verification.
Audit Metadata