{"answers":{"affected":"9 open source packages ship an affected version, including decepticon, decepticon-core and decepticon-sdk.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-61732 exists.","fix":"Upgrade decepticon to 1.1.17 or later.","what":"CVE-2026-61732 is a critical code injection vulnerability in BitterSecurity Decepticon, published on 24 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-61732 and fix it if it is affected.\n\nWhat it is: CVE-2026-61732 is a critical code injection vulnerability in BitterSecurity Decepticon, published on 24 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-61732 exists.\n\nAffected packages and fixed versions:\n- decepticon (PyPI): affected all versions; fixed in 1.1.17\n- decepticon (PyPI): affected all versions; fixed in 1.1.17\n- decepticon (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-core (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-core (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-core (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-sdk (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-sdk (PyPI): affected all versions; fixed in 1.1.17\n- decepticon-sdk (PyPI): affected all versions; fixed in 1.1.17\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-61732/ (Markdown: https://insights.sbomify.com/CVE-2026-61732/index.md)","id":"CVE-2026-61732","markdown":"https://insights.sbomify.com/CVE-2026-61732/index.md","name":"CVE-2026-61732","record":{"aliases":["GHSA-g5f9-3xfg-p9mf","PYSEC-2026-4032","PYSEC-2026-4033","PYSEC-2026-4034"],"analysis":{"component_type":"developer_tool","fix_type":"upgrade","impacts":["code_execution","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"Autonomous hacking agent","requires_auth":"none","summary":"Attackers can execute arbitrary commands by injecting ChatML tokens into web crawl outputs, bypassing agent guardrails in Decepticon.","user_interaction":"not_required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":10,"severity":"critical","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-74","name":"Improper Neutralization of Special Elements in Output Used by a Downstream Component"}],"description":"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.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":"2026-09-25","github_poc":1,"max_poc_stars":0,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-09-25T06:47:40Z","kind":"github_poc","ref":"https://github.com/InertFluid/cve-2026-61732-lab","stars":0,"title":"Benign, self-contained reproduction of CVE-2026-61732 (Decepticon ChatML role-boundary forgery)"}],"tier":"weaponised"},"has_fix":true,"headline":"Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context","id":"CVE-2026-61732","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":9,"n_references":2,"next":{"headline":"LightRAG: CORS Wildcard + Credentials Enables Any-Origin Credentialed Requests","id":"CVE-2026-61736"},"packages":[{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon","purl":null,"source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon","purl":"pkg:pypi/decepticon","source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon","purl":"pkg:pypi/decepticon","source":"PYSEC-2026-4032"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-core","purl":null,"source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-core","purl":"pkg:pypi/decepticon-core","source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-core","purl":"pkg:pypi/decepticon-core","source":"PYSEC-2026-4033"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-sdk","purl":null,"source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-sdk","purl":"pkg:pypi/decepticon-sdk","source":"GHSA-g5f9-3xfg-p9mf"},{"ecosystem":"PyPI","fixed":["1.1.17"],"introduced":["0"],"last_affected":[],"package":"decepticon-sdk","purl":"pkg:pypi/decepticon-sdk","source":"PYSEC-2026-4034"}],"prev":{"headline":"Missing authorization in recipes","id":"CVE-2026-61726"},"products":["Decepticon","decepticon-core","decepticon-sdk"],"published":"2026-09-24","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"yes","exploitation":"poc","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-09-24","vendors":["BitterSecurity"]},"summary":"Attackers can execute arbitrary commands by injecting ChatML tokens into web crawl outputs, bypassing agent guardrails in Decepticon.","url":"https://insights.sbomify.com/CVE-2026-61732/"}