payloads-nosqli
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides script templates (Python and Ruby) that automate the extraction of data from external servers. The logic of these scripts (e.g., character-by-character discovery) is controlled by the output of external network targets, creating a vulnerability surface for indirect manipulation of the agent's tasks.\n
- Ingestion points: External HTTP response bodies and status codes are ingested by scripts in
SKILL.md.\n - Boundary markers: None present in the provided exploitation templates.\n
- Capability inventory: The skill leverages outbound network capabilities via the
requests(Python) andhttpx(Ruby) libraries.\n - Sanitization: Scripts perform raw response matching and disable SSL verification (
verify=False), which is a security best practice violation that increases exposure to untrusted data.\n- [EXTERNAL_DOWNLOADS]: The skill references several well-known external security tools and research repositories, such as PayloadsAllTheThings, NoSQLMap, and OWASP documentation. These references are provided for educational and authorized testing purposes.
Audit Metadata