php-language-modern
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest project configuration files (specifically
composer.json) to determine the project's supported PHP version. This process involves the agent reading untrusted data from the codebase, which is a potential surface for indirect prompt injection if those files contain malicious instructions. - Ingestion points: Project metadata files accessed via the
fuse-ai-pilot:explore-codebasetool as described in the agent workflow inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the project files.
- Capability inventory: The skill enables the agent to generate PHP code and interact with various specialized agents for research and validation (
fuse-ai-pilot:research-expert,fuse-ai-pilot:sniper). - Sanitization: There are no explicit requirements for the agent to sanitize or validate the content of the configuration files before using them to guide its research and code generation.
Audit Metadata