Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Security audit
receipt-raccoon
Security checks for vulnerabilities and agentic risk
Overview
This skill locally parses user-provided receipt text and can save it to a user-chosen ledger, with no hidden network, credential, or background behavior found.
Install only if you are comfortable storing receipt-derived purchase history locally. Keep ledger files out of public repos and shared folders, and choose receipt and ledger paths deliberately because the script reads and writes the paths you provide.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (15)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 2. Run `scripts/receipt_parser.py parse --text "..."` or pipe via stdin.
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
The skill describes reading receipt files and appending parsed data to a JSONL ledger, which implies file read/write behavior, but it does not declare any tool scope or permissions. In an agent environment, missing explicit scope increases the chance of overbroad or unintended filesystem access because the runtime and user are not clearly informed of what file operations the skill requires.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill instructs users to accumulate receipts in a persistent JSONL ledger without warning that receipts can reveal sensitive purchase history, merchant patterns, dates, and possibly location or health-related inferences. Persisting this data without privacy guidance raises the risk of unintended retention, disclosure, or mishandling of personal financial information.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest describes extracting structured data from receipt text and generating spending reports, but does not mention persisting receipt data to storage. The code appends full parsed receipts to a ledger file, adding a stateful data-retention behavior beyond pure parsing/reporting.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
This markdown file states that receipts are accumulated in a JSONL ledger and spending reports are generated, but it does not warn users that receipt contents can reveal sensitive personal or financial information. For markdown files, omission of warnings about behaviours affecting user data or privacy is in scope for missing user warnings.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The markdown states that all amounts are assumed to be in USD and that the currency field is set to USD by default. This is a locale/currency policy constraint expressed in natural language, but the document does not present it as an opt-in choice or justify it as a region-specific tool.
- Content
Static analysis
No suspicious patterns detected.