adonisjs
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches markdown documentation from
adonisjs-docs-indexer.enzopita.comanddocs.adonisjs.com. These sources are used to provide the agent with current framework APIs and examples. - [COMMAND_EXECUTION]: Instructs the agent on project initialization and maintenance using standard commands like
npm init adonisjs@latestand the AdonisJSaceCLI tool (node ace serve). - [PROMPT_INJECTION]: The skill implements a surface for indirect prompt injection by design, as it ingests remote markdown data to provide context for code generation.
- Ingestion points: External URLs defined in
SKILL.mdfor index and full documentation fetching. - Boundary markers: Absent. The skill does not explicitly instruct the agent to use delimiters or sanitization when processing the fetched documentation.
- Capability inventory: The agent is expected to generate application code, modify files, and suggest the use of framework CLI tools.
- Sanitization: Absent. There is no requirement for the agent to validate or filter the content retrieved from external documentation sources.
Audit Metadata