Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

pageindex.

Scanned repository says: [Aug '26] ⚡ PageIndex Flash: fast tree index generation for text-based PDFs, now the default indexing method in PageIndex SDK local mode.

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 source

39k starsMITpushed 1d ago

0community interest

Votes show community interest, not safety. They never change this score.

AUTOMATED SIGNAL65/100CCCNot security certification
START HERE

Critical findings need attention.

Critical finding · details withheld for 30 days

Inspect the findings
WHAT THIS DOES NOT ESTABLISH

Runtime safety, real-world agent capability, fitness for your use case or independent certification.

Scan scope97 / 98Partial eligible-file selection · not the entire repository
Recorded findings10Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
01 / KNOW THE REPOSITORY

What the source
actually tells us.

Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.

INSPECTED SOURCE97 / 98Partial selection
READMEReadRepository-authored information
MANIFESTS3LICENSE, pyproject.toml, requirements.txt

Who it is for

  • Stated purpose · repository says · unreviewed

    [Aug '26] ⚡ PageIndex Flash: fast tree index generation for text-based PDFs, now the default indexing method in PageIndex SDK local mode.

    README.md:34
  • Stated purpose · repository says · unreviewed

    Scale PageIndex to Millions of Documents: PageIndex File System is a file-level tree indexing layer that lets PageIndex reason over an entire corpus, not just a single document.

    README.md:35
  • Stated purpose · repository says · unreviewed

    Inspired by AlphaGo, PageIndex replaces the vector index with a hierarchical tree index and lets an LLM reason its way through it, the way a human expert turns to and reads the right section of a long report. Retrieval happens in two steps:

    README.md:46

What it can do

No explicit capability or integration was extracted; that does not mean none exists.

What adoption takes

  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on litellm.

    requirements.txt:1
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on openai.

    requirements.txt:2
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on requests.

    requirements.txt:3
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on urllib3.

    requirements.txt:5
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on openai-agents.

    requirements.txt:6
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on mcp.

    requirements.txt:7

Limits and terms

  • Declared license · manifest declares · unreviewed

    A license or copying file is present; its terms have not been reviewed.

    LICENSE:1

Observed technical context

JavaScript · 1 selected filePython · 96 selected files

These are references in selected source files, not proof that a feature works at runtime.

Read from commit 1a060df at Oct 12, 2026, 5:09 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.

02 / FINDINGS FIRST

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: 6 exact runtime versions from requirements.txt checked against OSV.dev on Oct 12, 2026; 1 with known advisories. Reachability is not checked.

10 findings
CRITICAL

Critical finding · details withheld for 30 days

SEC002 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

REL003 · Guardrails & loop control

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

pageindex/utils.py:176
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

pageindex/utils.py:213
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

pageindex/utils.py:176
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

pageindex/utils.py:213
MAJOR

Domain ownership not verified

TRUST001 · Entity trust

Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.

SUGGESTED ACTION

Verify the domain using the Metal Mantra DNS TXT challenge.

pageindex.ai · location unavailable
MINOR

Privacy Policy link not confirmed

TRUST003 · Entity trust

No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.

SUGGESTED ACTION

Expose a clear Privacy Policy link on the official homepage.

pageindex.ai · location unavailable
MINOR

Terms link not confirmed

TRUST004 · Entity trust

No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.

SUGGESTED ACTION

Expose a clear Terms link on the official homepage.

pageindex.ai · location unavailable
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

pypdf2 3.0.1 (PyPI) has known advisories: GHSA-4vvm-4w3v-6mr8, PYSEC-2026-1835 (highest severity moderate). pypdf and PyPDF2 possible Infinite Loop when a comment isn't followed by a character

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

requirements.txt:9
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
97 of 98 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
04 / THE METHOD BEHIND THE NUMBER

Open the
calculation.

Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.

01

Security & privacy

2 findings · 25% weight
78/10019.5 pts
02

Guardrails & loop control

3 findings · 25% weight
54/10013.5 pts
03

Schema & tooling

2 findings · 20% weight
68/10013.6 pts
04

Token & cost efficiency

0 findings · 15% weight
100/10015.0 pts
05

Entity trust

3 findings · 15% weight
25/1003.8 pts
Inspect the current standard
USER REPORTS

Did pageindex 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.

Sign in with GitHub to add a report

SHARE THE EVIDENCE

A signal.
Not a seal.

Share the full report so its scope and limits travel with the score.

Metal Mantra automated signal 65/100, not certified