{"id":"CVE-2026-61732","summary":"Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context","details":"Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK (Bring Your Own Key) deployment model, users configure their own LLM credentials to any OpenAI-compatible endpoint. Most open-source and self-deployed model providers (vLLM, SGLang, Ollama, LM Studio, text-generation-webui, etc.) do not filter special-token literals from user content in their default configurations. Those literals are parsed into structural role-boundary token IDs, meaning an attacker string planted in a target web page forges a new operator turn the model treats as authoritative, bypassing Decepticon's agent guardrails and resulting in arbitrary command execution inside the Kali Linux sandbox. Version 1.1.17 patches the issue.","aliases":["GHSA-g5f9-3xfg-p9mf"],"modified":"2026-09-25T03:49:03.363579407Z","published":"2026-09-24T17:40:51.248Z","database_specific":{"osv_generated_from":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/61xxx/CVE-2026-61732.json","cna_assigner":"GitHub_M","cwe_ids":["CWE-74"]},"references":[{"type":"FIX","url":"https://github.com/BitterSecurity/Decepticon/commit/79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67"},{"type":"ADVISORY","url":"https://github.com/BitterSecurity/Decepticon/security/advisories/GHSA-g5f9-3xfg-p9mf"},{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/61xxx/CVE-2026-61732.json"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-61732"}],"affected":[{"ranges":[{"type":"GIT","repo":"https://github.com/bittersecurity/decepticon","events":[{"introduced":"0"},{"fixed":"79ee2aaf22f4c36a5b1968f6ca3f8086b6e35b67"}],"database_specific":{"extracted_events":[{"introduced":"0"},{"fixed":"1.1.17"}],"source":"AFFECTED_FIELD"}}],"versions":["v1.1.16","v1.1.15","v1.1.14","v1.1.13","v1.1.12","v1.1.11","v1.1.10","v1.1.9","v1.1.8","v1.1.7","v1.1.6","v1.1.5","v1.1.4","v1.1.3","v1.1.2","v1.1.1","v1.1.0","v1.0.27","v1.0.26","v1.0.25","v1.0.24","v1.0.23","v1.0.22","v1.0.21","v1.0.20","v1.0.19","v1.0.18","v1.0.17","v1.0.16","v1.0.15","v1.0.14","v1.0.13","v1.0.12","v1.0.11","v1.0.10","v1.0.9","v1.0.8","v1.0.7","v1.0.6","v1.0.5","v1.0.4","v1.0.3","v1.0.2","v1.0.1","v1.0.0"],"database_specific":{"source":"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-61732.json"}}],"schema_version":"1.9.0","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H"}]}