Scanned repository says: Dexter takes complex financial questions and turns them into clear, step-by-step research plans. It runs those tasks using live market data, checks its own work, and refines the results until it has a confident, data-backed answer.
Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.
Inspect GitHub sourceVotes show community interest, not safety. They never change this score.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
Dexter takes complex financial questions and turns them into clear, step-by-step research plans. It runs those tasks using live market data, checks its own work, and refines the results until it has a confident, data-backed answer.
README.md:34Intelligent Task Planning: Automatically decomposes complex queries into structured research steps
README.md:37Autonomous Execution: Selects and executes the right tools to gather financial data
README.md:38No explicit capability or integration was extracted; that does not mean none exists.
Bun runtime (v1.0 or higher)
README.md:50Declares a dependency on @langchain/core.
package.json:22Declares a dependency on zod.
package.json:44Declares a dependency on @langchain/anthropic.
package.json:21Declares a dependency on @langchain/exa.
package.json:23Declares a dependency on @langchain/google-genai.
package.json:24Declares a dependency on @langchain/ollama.
package.json:25No explicit limitation or license statement was extracted; that does not mean none exists.
These are references in selected source files, not proof that a feature works at runtime.
Read from commit 534f6be at Oct 12, 2026, 5:05 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Dependencies: 249 exact runtime versions from package-lock.json checked against OSV.dev on Oct 12, 2026; 14 with known advisories. Reachability is not checked.
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
The stated website could not be reached over HTTPS, so Metal Mantra could not confirm it is a secure, working site.
Make the official website reachable over HTTPS for verification.
@whiskeysockets/baileys 7.0.0-rc.9 (npm) has a known advisory: GHSA-qvv5-jq5g-4cgg (highest severity critical). Baileys has message upsert / hist sync spoofing and app state corruption when using maliciously crafted protocolMessage payload
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
js-yaml 3.14.2 (npm) has known advisories: GHSA-2883-xcg3-v3hh, GHSA-52cp-r559-cp3m, GHSA-5p4m-2wfm-xmqj, GHSA-h67p-54hq-rp68 (highest severity high). js-yaml: maxTotalMergeKeys does not limit CPU use for empty merge sources
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
langsmith 0.5.13 (npm) has known advisories: GHSA-3644-q5cj-c5c7, GHSA-fw9q-39r9-c252, GHSA-rr7j-v2q5-chgv (highest severity high). LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
The code returns the model's raw text. Output that was never parsed or validated can pass mistakes straight to users or other systems.
Parse and validate the result before returning it.
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
@protobufjs/utf8 1.1.0 (npm) has a known advisory: GHSA-q6x5-8v7m-xcrf (highest severity moderate). protobufjs has overlong UTF-8 decoding
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
file-type 21.3.0 (npm) has known advisories: GHSA-5v7r-6r5c-r473, GHSA-j47w-4g3g-c36v (highest severity moderate). file-type affected by infinite loop in ASF parser on malformed input with zero-size sub-header
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
music-metadata 11.12.0 (npm) has known advisories: GHSA-53v6-4h7p-p4gj, GHSA-5gfj-9q3v-qfp3, GHSA-8j4c-6x6g-rq3j, GHSA-f94x-6692-553q, GHSA-jjpr-9cvf-cq55 (highest severity moderate). music-metadata: Uncontrolled memory allocation in APEv2 parser
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
Share the full report so its scope and limits travel with the score.
