ClawHub

GLM-OCR-Formula

v1.0.3

Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equation...

⭐ 1· 265·1 current·1 all-time
byJared Wen@jaredforreal
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the actual behavior: the skill requires a ZhiPu API key, uses python, and calls the ZhiPu layout_parsing endpoint. Required env vars (ZHIPU_API_KEY, GLM_OCR_TIMEOUT) and the included CLI script are appropriate for the declared function.
ℹ
Instruction Scope
SKILL.md instructs the agent to run the included Python script and explicitly forbids local parsing/fallbacks; it also asks the agent to remember the user's LaTeX display preference for the session. The instructions do not ask the agent to read unrelated system files or other credentials, but the 'never offer alternatives' restriction is strict (design choice) and means no local OCR fallback will be attempted even if desirable.
✓
Install Mechanism
No install spec (instruction-only) reduces risk. The code file depends on the widely used 'requests' library; the script prints an installation hint if requests is missing. No downloads from untrusted URLs or archive extraction are present.
✓
Credentials
Only ZHIPU_API_KEY (primary credential) and an optional timeout env var are required, which are proportional to a cloud OCR integration. The skill documents the fixed official endpoint and does not support overriding it, which reduces exfiltration risk.
✓
Persistence & Privilege
always is false and the skill does not request persistent or system-wide privileges. The SKILL.md asks the agent to remember a user preference during the session (agent memory), which is normal and not a system-level persistence request.
Assessment
This skill will send your image/PDF bytes and any extracted text to ZhiPu's API using the ZHIPU_API_KEY you provide. Before installing, consider: (1) Do you trust sending these documents to the ZhiPu service? (2) Use a skill-level API key or limit scope if you don't want the same key shared across other ZhiPu skills. (3) The script requires the Python 'requests' package—install it if missing. (4) The skill deliberately forbids local fallback parsing, so it will not attempt local OCR if the API fails. (5) If you process sensitive documents, review ZhiPu's privacy/retention policy and consider redacting or testing with non-sensitive examples first.

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

latestvk97fb2teze34xn8xcp5mhx2y318397bg

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

📐 Clawdis
Binspython
EnvZHIPU_API_KEY, GLM_OCR_TIMEOUT
Primary envZHIPU_API_KEY

Comments