{"id":"CVE-2026-55520","state":"PUBLISHED","title":"Protego: Exponential backtracking ReDoS in robots.txt URL wildcard matching","description":"Protego is a pure-Python robots.txt parser with support for modern conventions. Prior to 0.6.2, protego._urlpattern._URLPattern._prepare_pattern_for_regex translates every asterisk in an Allow or Disallow directive into a lazy regular-expression wildcard, so a directive containing many asterisks creates exponential backtracking. After protego.Protego.parse processes a crafted robots.txt file, protego.Protego.can_fetch can spend an attacker-controlled period matching a near-miss URL and deny service to the crawler. The vulnerable path is src/protego/_urlpattern.py in the _URLPattern match logic. This issue is fixed in version 0.6.2.","publishedAt":"2026-08-28T18:42:38.334Z","updatedAt":"2026-08-31T18:54:01.091Z","severity":{"score":7.1,"label":"High","version":"4.0","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","source":"GitHub_M"},"assigner":"GitHub_M","products":["scrapy protego"],"affected":[{"vendor":"scrapy","product":"protego","versions":[{"version":"< 0.6.2","status":"affected"}]}],"references":["https://github.com/scrapy/protego/security/advisories/GHSA-wjmf-p669-5m5p","https://github.com/scrapy/protego/commit/785940181659bf440ba82f1da148fade5087e858","https://github.com/scrapy/protego/releases/tag/0.6.2"],"weaknesses":["CWE-400","CWE-1333"],"ingestedAt":"2026-10-29T20:12:24.861Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/55xxx/CVE-2026-55520.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-55520","state":"PUBLISHED","datePublished":"2026-08-28T18:42:38.334Z","dateUpdated":"2026-08-31T18:54:01.091Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-06-16T22:44:22.284Z"},"containers":{"cna":{"title":"Protego: Exponential backtracking ReDoS in robots.txt URL wildcard matching","descriptions":[{"lang":"en","value":"Protego is a pure-Python robots.txt parser with support for modern conventions. Prior to 0.6.2, protego._urlpattern._URLPattern._prepare_pattern_for_regex translates every asterisk in an Allow or Disallow directive into a lazy regular-expression wildcard, so a directive containing many asterisks creates exponential backtracking. After protego.Protego.parse processes a crafted robots.txt file, protego.Protego.can_fetch can spend an attacker-controlled period matching a near-miss URL and deny service to the crawler. The vulnerable path is src/protego/_urlpattern.py in the _URLPattern match logic. This issue is fixed in version 0.6.2."}],"affected":[{"vendor":"scrapy","product":"protego","versions":[{"version":"< 0.6.2","status":"affected"}]}],"references":[{"url":"https://github.com/scrapy/protego/security/advisories/GHSA-wjmf-p669-5m5p","name":"https://github.com/scrapy/protego/security/advisories/GHSA-wjmf-p669-5m5p","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/scrapy/protego/commit/785940181659bf440ba82f1da148fade5087e858","name":"https://github.com/scrapy/protego/commit/785940181659bf440ba82f1da148fade5087e858","tags":["x_refsource_MISC"]},{"url":"https://github.com/scrapy/protego/releases/tag/0.6.2","name":"https://github.com/scrapy/protego/releases/tag/0.6.2","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV4_0":{"attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"PASSIVE","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","baseScore":7.1,"baseSeverity":"HIGH","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","version":"4.0"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-400","lang":"en","description":"CWE-400: Uncontrolled Resource Consumption","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-1333","lang":"en","description":"CWE-1333: Inefficient Regular Expression Complexity","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-08-28T18:42:38.334Z"},"source":{"advisory":"GHSA-wjmf-p669-5m5p","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-08-31T15:42:18.385319Z","id":"CVE-2026-55520","options":[{"Exploitation":"none"},{"Automatable":"yes"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-08-31T18:54:01.091Z"}}]}}}