payloads-idor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The testing workflow requires the agent to interact with and analyze responses from external web applications, creating a potential surface where an attacker-controlled target could return data containing malicious instructions aimed at the agent.\n
- Ingestion points: The workflow in
SKILL.md(Step 1: Recon & Identification and Step 3: Exploitation) requires the agent to identify injection points, enumerate endpoints, and capture evidence (HTTP logs, curl output) from external systems.\n - Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions embedded in the data being audited.\n
- Capability inventory: The skill is a documentation-only asset and contains no executable scripts, shell tools, or system-level capabilities.\n
- Sanitization: The workflow does not include steps for sanitizing or filtering data received from external systems during the audit process.\n- [NO_CODE]: The skill is composed entirely of markdown documentation and contains no scripts, binaries, or configuration files that execute on the local system.
Audit Metadata