paradedb-skill
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from
https://docs.paradedb.com. This is a vendor-controlled domain used to provide the agent with current context. - [COMMAND_EXECUTION]: The skill includes a helper script at
scripts/paradedb-docswhich executescurl. The script implements basic safety checks by validating file extensions (.md or .txt) and hardcoding the target domain to prevent unauthorized network access. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting external content into the agent's context.
- Ingestion points: Remote documentation is fetched via
scripts/paradedb-docsand loaded into the session. - Boundary markers: The instructions do not define specific delimiters for the fetched content.
- Capability inventory: The agent is authorized to execute the documentation fetching script.
- Sanitization: The script limits file types, though the agent is instructed to treat the resulting content as context.
Audit Metadata