payment
2 findings (1 high, 1 medium), mainly unauthorized tool use, social engineering. Most recent scan 2026-02-06.
This payment processing skill presents SIGNIFICANT SECURITY RISKS due to the complete absence of implementation code despite claiming comprehensive payment functionality. The combination of 'always: True' auto-activation, missing credential management implementation, and lack of security controls creates a dangerous scenario where the agent would improvise financial transaction code at runtime. The skill appears to be an incomplete template or placeholder that should NOT be used for actual payment processing without substantial security hardening. Key risks include potential credential exposure, tool shadowing leading to unsafe payment API calls, missing resource controls, and misleading capability claims. This skill requires complete implementation with security review before any production use.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco rates this HIGH and SkillSpector found nothing. Check the false-positive register; signature matches on documentation are the usual cause. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Payment processing and management. Handle invoices, transactions, and payment gateway integrations.
- Package
- 1 file, 735 B
- SKILL.md
- 78 words, 5 sections
- Code
- None. Instructions only.
- Requires
- bins:
curljq
SKILL.md covers: Payment 💳 · Features · Supported Gateways · Usage Examples · Safety Rules
Findings
HIGH Tool Shadowing Risk - Missing Implementation Creates Execution Ambiguity Unauthorized Tool Usellm
The skill declares 'always: True' in clawdbot metadata, meaning it will be automatically activated for payment-related queries. However, there are NO script files implementing the claimed functionality (invoicing, payment processing, refunds, transaction tracking). This creates a 'tool shadowing' scenario where the agent may attempt to fulfill payment requests using unrestricted Bash/Python execution since no safe implementation exists. The agent could generate arbitrary payment-processing code at runtime without guardrails.
SKILL.md
Metadata shows 'always: True' and 'requires: {bins: [curl, jq]}' suggesting network operations, but zero implementation scripts exist. Agent will have to improvise payment processing logic, potentially executing unsafe curl commands to payment APIs.MEDIUM Misleading Capability Claims Without Implementation Social Engineeringllm
The skill description and features list claim comprehensive payment processing capabilities (invoicing, payment processing, refunds, transaction tracking, multiple gateway support) but contains zero implementation code. This is deceptive as users may believe the skill provides secure, tested payment functionality when in reality the agent would need to generate payment-handling code on-the-fly, which is extremely risky for financial operations.
SKILL.md
Features section lists: 'Create and send invoices', 'Process payments', 'Track payment status', 'Refund management', 'Payment history' and claims support for Stripe, PayPal, Square, and crypto payments. However, 'Script Files: No script files found.'What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 735 B |
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/payment
- Raw scan result: payment-scan.json
- Badge for your README:
- Request a re-scan