Specification Extractor

v2.1.0

Extract structured data from construction specifications. Parse CSI sections, requirements, submittals, and product data from spec documents.

0· 1.3k·4 current·4 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name/description, instructions, and required capabilities align: parsing PDF specs naturally requires Python (for the provided example implementation) and filesystem access to read user documents. There are no unrelated credentials, services, or binaries requested.
Instruction Scope
SKILL.md shows parsing of PDFs (pdfplumber + regex) and extraction of sections/products/submittals — this stays within the stated scope. The instructions ask to use data provided by the user. I did not observe any directives to read unrelated system files, access environment secrets, or transmit data to external endpoints in the provided excerpts. Review the full SKILL.md for any hidden networking calls, but the visible content is focused on local document parsing.
Install Mechanism
There is no install spec (instruction-only), which is low risk. However, the example code uses the third-party package pdfplumber (and possibly other Python libs) but the skill does not declare how those Python dependencies should be installed. That mismatch is an operational issue (missing dependency installation instructions) rather than a security red flag.
Credentials
The skill requests no environment variables or credentials. claw.json declares a 'filesystem' permission which is proportionate to the task of reading user-supplied spec files. No other sensitive access is requested.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent global presence or elevated privileges. There is no indication it modifies other skills or system-wide settings.
Assessment
This skill appears coherent and focused on extracting data from PDFs. Before installing or running it: (1) confirm you have python3 and install required Python packages (e.g., pdfplumber) in a controlled environment; the skill doesn't include an install step for those dependencies. (2) Only feed non-sensitive example files at first to validate behavior. (3) Review the full SKILL.md/instructions for any network calls or pip/exec commands not shown in the excerpt. (4) Note that filesystem permission is required to read your documents — ensure you trust the skill owner or run it in an isolated environment if handling confidential specs.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bcws58z93v2qw87pac8b18s816445

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📑 Clawdis
OSmacOS · Linux · Windows
Binspython3

Comments