Is pdf-text-extract safe to install?

SaferSkills independently audited pdf-text-extract (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/pdf-text-extract/SKILL.md · 1 file

skills/pdf-text-extract/SKILL.md2.2 KB · Markdown

name: pdf-text-extract

description: "Extract text and simple table-like rows from a PDF for downstream AI without OCR binaries. Use when the user asks to read a PDF, turn a PDF into text, pull simple tables from statements/reports, or feed PDF content into an LLM pipeline."

version: "1.0.0"

PDF Text Extract

Use this skill when a workflow needs machine-readable text from a digital PDF before summarization, classification, or structured extraction. The helper uses pure-Python PDF libraries when available and includes a simple line-based table detector for downstream cleanup.

When to invoke

User says: "extract text from this PDF", "feed a PDF to AI", "pull tables from this report", "read this statement".
The PDF already contains selectable text and does not require OCR.

When NOT to invoke

The PDF is a scanned image; use an OCR workflow instead.
The user needs pixel-perfect table reconstruction with merged cells and layout fidelity.

Concrete example

User input:

Extract the text and rough tables from this PDF so Gemini can summarize it.

Output:

# Copy assets/extract.py into your project, then:
from extract import extract_pdf

doc = extract_pdf("downloads/report.pdf")
print(doc["text"][:2000])
for table in doc["tables"]:
    print(table["page"], table["rows"][:3])

Install either pypdf or pdfminer.six in the target project. No OCR binary is required, and the helper fails clearly when the PDF has no extractable text.

Pattern to apply

Prefer digital text extraction first; do not add OCR unless the source is scanned.
Preserve page boundaries so downstream prompts can cite page numbers.
Keep table extraction simple: split rows on tabs or repeated spaces, then let a later schema pass normalize columns.
Cap text sent to an LLM by page/range when the PDF is long.
Fail loudly when no text is found instead of sending an empty prompt downstream.

Reference: assets/extract.py.

Source

Distilled from production use across the author's automation projects. v1.0.0. See also: [[gemini-structured-output]], [[csv-report-writer]], [[s3-uploader]].

→ Build the full runnable bot with Trawlkit.

pdf-text-extract— agent skill

Is pdf-text-extract safe to install?

PDF Text Extract

When to invoke

When NOT to invoke

Concrete example

Pattern to apply

Source

Audit the pieces. Scan the whole. Decide.