web-auth-bypass
Warn
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install the
jwt_toolutility from an external GitHub repository (https://github.com/ticarpi/jwt_tool.git) which is not associated with a trusted organization or well-known service. It also lists several non-standard Python and Node.js packages as requirements. - [INDIRECT_PROMPT_INJECTION]: The skill operates by fetching and processing untrusted data from external web applications using
curl,requests, andWebFetch. This creates a vulnerability surface for indirect prompt injection attacks where the processed data could contain instructions targeting the agent. - Ingestion points: Responses from web applications targeted for testing as seen in
SKILL.md,payloads.md, and various guides. - Boundary markers: Not present; the skill lacks delimiters or instructions for the agent to ignore commands within the fetched content.
- Capability inventory: The skill uses
Bashfor network operations andWritefor managing tokens and scan results locally. - Sanitization: No evidence of filtering or escaping external data before it is integrated into the agent's workflow.
- [COMMAND_EXECUTION]: The skill provides numerous Bash and Python scripts designed for the agent to perform network-based attacks. These scripts involve automated login attempts and parallel requests to external network services.
Audit Metadata