laravel-attributes
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and directs the agent to fetch documentation and code examples from a GitHub repository owned by the author.
- Evidence: Links to
https://github.com/MrPunyapal/laravel-attributes-list/blob/main/README.mdandhttps://github.com/MrPunyapal/laravel-attributes-list/tree/main/attributesinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read content from an external repository to guide its code generation, which introduces a vulnerability surface if the external source is compromised.
- Ingestion points: External file content from the
attributes/directory on GitHub referenced inSKILL.md. - Boundary markers: None identified; the skill does not instruct the agent to ignore potentially malicious instructions embedded in the external content.
- Capability inventory: The agent is tasked with writing and reviewing PHP code, including Models, Jobs, Commands, and Controllers.
- Sanitization: No sanitization or validation of the fetched external content is specified.
- [METADATA_POISONING]: The skill name and description claim support for "Laravel 13+", which is a version of the framework that has not been released. This misleading information could cause the agent to suggest non-standard or incompatible code patterns.
- Evidence: The
nameanddescriptionfields in the YAML frontmatter ofSKILL.md.
Audit Metadata