Receipt and Expense Reconciler
v1.0.0Parse receipts and invoices, categorize spend, detect anomalies, and produce tax-ready expense summaries for freelancers and SMB operators.
⭐ 0· 104·0 current·0 all-time
byASP@anugotta
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description, declared capabilities, and required resources are coherent: a receipt/invoice reconciler doesn't require external credentials or platform installs by default. The SKILL.md describes expected inputs (PDF/image/text/CSV) and outputs (parsed records, summaries) which align with the stated purpose.
Instruction Scope
Instructions are high-level and do not include explicit commands, external endpoints, or code. That keeps the scope narrow, but the term 'Ingest receipts/invoices (PDF/image/text/CSV)' gives the agent broad discretion to request or read many user files; the skill does not specify whether processing is local or via external OCR/API services. This ambiguity is worth noting for privacy/operational reasons.
Install Mechanism
No install spec and no bundled code files — instruction-only skill. This minimizes disk-write and install risk.
Credentials
The skill declares no environment variables, credentials, or config paths. Nothing requested appears disproportionate to the stated task.
Persistence & Privilege
The skill is not always-enabled and does not request persistent privileges or modification of other skills. Autonomous invocation is allowed by default but is not combined with other concerning permissions.
Assessment
This skill appears to be what it says, but it is purely an instruction sheet with no implementation details. Before using: 1) Confirm where processing will occur (local vs cloud OCR/API). If cloud services will be used, ask which endpoints and whether you must supply API keys. 2) Limit uploads to only necessary receipts and avoid sending sensitive PII unless you trust the processing location. 3) Test with non-sensitive sample data first to verify outputs and how duplicates/anomalies are flagged. 4) If you need automated runs or integration with accounting software, require explicit details about what will be installed or what credentials are needed. If those details are provided later, re-evaluate for proportionality and network/credential use.Like a lobster shell, security has layers — review code before you run it.
latestvk978hh1t5bxqz063nc7r7exx59837drz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧾 Clawdis
