paywall-teardown
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The instructions include specific python3 commands used for internal randomization of design choices. These commands are executed locally by the agent using static code defined in the skill's reference files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs including screenshots, renders, and JSON configurations. This creates a potential surface for indirect prompt injection if the ingested data contains adversarial text designed to influence the agent's behavior, though instructions are provided to focus only on visual/config analysis.
- [EXTERNAL_DOWNLOADS]: The skill references a legitimate URL for the vendor's no-code builder tool (adapty.io). This is a well-known service associated with the skill's author.
Audit Metadata