detect-code-smells
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of PHP codebases, which creates a surface for indirect prompt injection if the analyzed files contain instructions designed to manipulate the agent.
- Ingestion points: The skill reads content from all files matching the
**/*.phppattern within the project directory. - Boundary markers: The instructions do not define clear delimiters or provided specific "ignore" instructions for content found within the codebase.
- Capability inventory: The skill uses shell-based tools including
grep,find,awk, andwcto process file contents. - Sanitization: No sanitization or validation of the data read from files is performed before it is presented to the agent for analysis.
Audit Metadata