Enviar #822018: NousResearch hermes-agent <= v2026.4.30 Improper Input Validation (CWE-20)información

TítuloNousResearch hermes-agent <= v2026.4.30 Improper Input Validation (CWE-20)
Descripción# Technical Details A Prompt Injection Filter Bypass exists in the `_serve_plugin_skill` and `skill_view` methods in `tools/skills_tool.py` of hermes-agent. The application fails to use robust regex matching for prompt injection detection, relying instead on naive exact-string substring matching via the `in` operator. # Vulnerable Code File: tools/skills_tool.py Method: _serve_plugin_skill / skill_view Why: `_INJECTION_PATTERNS` defines static literal strings, and the methods use `p in content.lower()` which only matches exact contiguous character sequences, failing to catch multi-word variants or synonym substitutions. # Reproduction 1. Set up the hermes-agent environment: `export HERMES_ROOT=$(pwd)` 2. Download and execute the exploit PoC script (https://gist.github.com/YLChen-007/88d745b9bcd3d49d47427a0f7b2308e7) via `python3 poc_exploit.py`. 3. Observe that prompt payloads with extra words or synonym substitutions successfully bypass the filter and are injected into the agent's context. # Impact - Exfiltration of sensitive data (environment variables, API keys, file contents). - Execution of arbitrary commands via the agent's shell tool, and override of safety constraints.
Fuente⚠️ https://gist.github.com/YLChen-007/9dd399c6f75b31fa741a613dfd41de08
Usuario
 Eric-j (UID 98073)
Sumisión2026-05-07 15:38 (hace 28 días)
Moderación2026-05-31 09:51 (24 days later)
EstadoAceptado
Entrada de VulDB367499 [NousResearch hermes-agent hasta 2026.4.30 tools/skills_tool.py _serve_plugin_skill/skill_view escalada de privilegios]
Puntos20

Do you want to use VulDB in your project?

Use the official API to access entries easily!