Who it is for
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
pyproject.toml:8
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2
serena.
Scanned repository says: A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
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 source0community interest
Votes show community interest, not safety. They never change this score.
62/100CCCNot security certification
Critical findings need attention.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Scan scope200 / 206Partial eligible-file selection · not the entire repository
Recorded findings14Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
What the source
actually tells us.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
200 / 206Partial selection
ReadRepository-authored information
2LICENSE, pyproject.toml
What it can do
Serena provides a wide range of tools for efficient code retrieval, editing and refactoring, as well as
README.md:128
What adoption takes
Manifest declares Python >=3.11, <3.15 as a requirement.
pyproject.toml:11Declares a dependency on requests.
pyproject.toml:21Declares a dependency on overrides.
pyproject.toml:22Declares a dependency on python-dotenv.
pyproject.toml:23Declares a dependency on mcp.
pyproject.toml:24Declares a dependency on click.
pyproject.toml:25Declares a dependency on flask.
pyproject.toml:26
Limits and terms
A license or copying file is present; its terms have not been reviewed.
LICENSE:1
Observed technical context
JavaScript · 2 selected filesPython · 198 selected files
These are references in selected source files, not proof that a feature works at runtime.
Read from commit 1de556f at Oct 12, 2026, 5:18 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
02 / FINDINGS FIRSTWhat needs
What needs
a closer look.
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: 85 exact runtime versions from uv.lock checked against OSV.dev on Oct 12, 2026; 6 with known advisories. Reachability is not checked.
14 findings
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
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.
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
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.
MAJORUnsafe deserialization
Unsafe deserialization
The code loads data with a format that can run code while it is read, such as pickle or unrestricted YAML. A poisoned file, cache entry or downloaded model then runs with the agent's permissions.
Use a data-only format (JSON, safetensors, yaml.safe_load) for anything that is not fully trusted.
MAJORUnsafe deserialization
Unsafe deserialization
The code loads data with a format that can run code while it is read, such as pickle or unrestricted YAML. A poisoned file, cache entry or downloaded model then runs with the agent's permissions.
Use a data-only format (JSON, safetensors, yaml.safe_load) for anything that is not fully trusted.
MAJORDomain ownership not verified
Domain ownership not verified
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.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
anyio 4.13.0 (PyPI) has known advisories: GHSA-5p39-cfhj-2xmp, GHSA-82r6-8w77-94w6, PYSEC-2026-4024, PYSEC-2026-4025 (highest severity critical). AnyIO: TLSStream IDNA 2003 host name encoding enables potential TLS certificate spoofing
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
httpcore2 2.9.1 (PyPI) has known advisories: GHSA-7mj9-2mp8-4m2p, PYSEC-2026-3844 (highest severity high). HTTPX2: Secure WebSocket traffic sent without TLS through SOCKS proxies
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MAJORDependency with a high-severity advisory
Dependency with a high-severity advisory
httpx2 2.9.1 (PyPI) has known advisories: GHSA-7mj9-2mp8-4m2p, GHSA-8xx6-hgc6-gc2m, GHSA-f2fp-rgf2-35cp, GHSA-h4x7-gw46-3wm6, GHSA-pf96-p4fj-6566 (highest severity high). HTTPX2: Secure WebSocket traffic sent without TLS through SOCKS proxies
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORRaw model text returned
Raw model text returned
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.
MINORPrivacy Policy link not confirmed
Privacy Policy link not confirmed
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.
MINORTerms link not confirmed
Terms link not confirmed
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.
MINORDependency with a known advisory
Dependency with a known advisory
pyjwt 2.13.0 (PyPI) has known advisories: GHSA-2gx3-rcp4-g85q, GHSA-42vr-xj54-vc7v, GHSA-8wjv-2p76-3863, GHSA-9j54-fg26-wv3r, GHSA-9v7f-9g4p-ffgj (highest severity moderate). PyJWT: PyJWKClient still amplifies unauthenticated JWKS fetches on unknown kid values (incomplete fix of CVE-2026-48524)
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORDependency with a known advisory
Dependency with a known advisory
soupsieve 2.8.4 (PyPI) has known advisories: GHSA-gjv8-xp57-g29c, GHSA-j934-xhv5-fg8f, PYSEC-2026-4170, PYSEC-2026-4171 (highest severity moderate). Soup Sieve: Polynomial-time ReDoS (O(n²)) in the `IDENTIFIER` / `VALUE` selector sub-patterns
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
MINORDependency with a known advisory
Dependency with a known advisory
werkzeug 3.1.7 (PyPI) has a known advisory: GHSA-g6x2-hccm-hh4m (highest severity moderate). Werkzeug safe_join() allows Windows special device names
Upgrade to a fixed version listed in the advisory and regenerate the lockfile.
The boundary
is part of the result.
- What was scanned
- 200 of 206 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution. - What remains unknown
- Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
- Source location
- Links open the current repository HEAD. Source may have changed since this snapshot.
- Something looks wrong?
- Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
- Entity trust · 15% of v0.2
- Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
Open the
calculation.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
Security & privacy
0/100
Guardrails & loop control
100/100
Schema & tooling
92/100
Token & cost efficiency
100/100
Entity trust
25/100
Did serena work for people?
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 EVIDENCEA signal.
A signal.
Not a seal.
Share the full report so its scope and limits travel with the score.
