{"data":{"id":"c97a5db8-4419-4e37-ab35-0fc31bf88193","title":"CVE-2026-29872: A cross-session information disclosure vulnerability exists in the awesome-llm-apps project in commit…","summary":"CVE-2026-29872 is a cross-session information disclosure flaw in the awesome-llm-apps project at commit e46690f99c3f08be80a9877fab52acacf7ab8251 (2026-01-19). The Streamlit-based GitHub MCP Agent stores user-supplied API tokens in process-wide environment variables via os.environ without session isolation, so credentials from one user stay readable by later unauthenticated users. An attacker could retrieve GitHub Personal Access Tokens or LLM API keys, enabling unauthorized access to private resources and financial abuse.","solution":"N/A -- no mitigation discussed in source.","labels":["security","privacy"],"sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-29872","publishedAt":"2026-03-30T18:16:18.523Z","cveId":"CVE-2026-29872","cweIds":["CWE-200","CWE-284","CWE-522"],"cvssScore":"8.2","cvssSeverity":"high","severity":"high","attackType":["data_extraction"],"issueType":"vulnerability","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["awesome-llm-apps","GitHub MCP Agent","Streamlit"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":"awesome-llm-apps cross-session disclosure of API tokens in GitHub MCP Agent","headlinePromptVersion":"h1","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N","attackVector":"network","attackComplexity":"low","privilegesRequired":"none","userInteraction":"none","exploitMaturity":"unknown","epssScore":0.00269,"epssCheckedAt":"2026-11-19T12:10:37.334Z","kevDateAdded":null,"advisoryAliases":["GHSA-qx64-h3hh-3vhj"],"affectedPackagesSource":null,"affectedPackagesCheckedAt":"2026-11-18T00:16:55.990Z","patchAvailable":null,"disclosureDate":"2026-03-30T18:16:18.523Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":["CAPEC-116"],"crossRefCount":0,"attackSophistication":"trivial","impactType":["confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":null,"atlasIds":null,"fixes":[]}}