Lab Budget Forecaster
v1.0.0Use lab budget forecaster for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.
⭐ 0· 54·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the packaged artifact (scripts/main.py). No unrelated binaries, credentials, or config paths are requested.
Instruction Scope
SKILL.md directs local execution (py_compile and running scripts/main.py) and to validate inputs; it mentions editing an in-file "CONFIG" block that does not exist in the provided code — a minor documentation mismatch but not a security concern. The instructions do not ask to read unrelated files, call external endpoints, or access secrets.
Install Mechanism
No install spec included (instruction-only). The runtime uses only standard Python libraries; nothing is downloaded or written to disk beyond normal script execution.
Credentials
No environment variables, credentials, or external service tokens are requested or required.
Persistence & Privilege
Skill is not always-enabled and does not request persistent/global agent privileges or modify other skills' configuration.
Assessment
This skill appears to be what it says: a small, local Python reporter for budget runway. Before running it: 1) inspect scripts/main.py yourself (it’s short and readable) and run python -m py_compile to confirm syntax; 2) run the script in a sandboxed environment or isolated workspace if you will process real financial data; 3) validate CSV input paths (no untrusted paths or symlinks) and avoid passing sensitive credentials (none are required); 4) be aware of a few minor implementation issues — percent_used will raise on a zero budget (division by zero), burn-rate/date math can produce unexpected results if expense dates precede the start date, and the depletion prediction uses datetime.now() rather than the grant end date — consider these if you need strict correctness; and 5) if you rely on this in production, add input validation, pin Python/dependency versions, and add tests for edge cases. Overall there are no signs of network exfiltration, secret access, or unexpected elevated privileges.Like a lobster shell, security has layers — review code before you run it.
latestvk973m3zwzdtsh8mwwxdw0n3t1s83npx3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
