configuring-horizon
Warn
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: MEDIUMMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill metadata identifies the author as "laravel", which conflicts with the actual source and could lead to misjudgment of the skill's official status.
- [INDIRECT_PROMPT_INJECTION]: The skill uses the search-docs tool to fetch external information that directly informs the agent's actions. 1. Ingestion points: Data is retrieved via search-docs as specified in SKILL.md. 2. Boundary markers: There are no instructions to differentiate between the agent's core rules and data retrieved from documentation. 3. Capability inventory: The skill is capable of executing artisan commands and modifying application code (SKILL.md). 4. Sanitization: There is no validation or filtering of the content retrieved from external searches before it is processed by the agent.
Audit Metadata