web-auth-jwt
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process externally provided authentication tokens, which represents a potential attack surface.
- Ingestion points: Raw JWT strings are ingested as arguments for CLI tools in SKILL.md and cheatsheet.md.
- Boundary markers: The skill lacks instructions for the agent to use delimiters or ignore embedded instructions within the token payloads or tool outputs.
- Capability inventory: The skill involves the execution of various shell-based security tools such as jwt_tool, hashcat, and john as documented in cheatsheet.md.
- Sanitization: No input validation, escaping, or structural verification is recommended for the tokens before they are passed to external subprocesses.
Audit Metadata