solid-php
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project files (codebase exploration) which constitutes untrusted input. Maliciously crafted content within the analyzed project could attempt to influence the behavior of the primary agent or the sub-agents it spawns during implementation and validation.
- Ingestion points: Local project files, directory structures, and configuration files like
module.jsonacross theFuseCore/directory. - Boundary markers: Absent; there are no instructions to wrap external code content in delimiters or ignore embedded instructions during analysis.
- Capability inventory: The skill allows for codebase-wide searching (grep), file creation, file modification (refactoring), and the spawning of additional specialized agents (
fuse-ai-pilot:explore-codebase,fuse-ai-pilot:research-expert,fuse-ai-pilot:sniper). - Sanitization: Absent; the skill does not specify validation or sanitization steps for the data ingested from the project files.
Audit Metadata