Back to skill

Security audit

expense-tracker

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward local expense tracker, but it stores sensitive financial records without enforcing private file permissions despite claiming the data is fully private.

Review this before installing if you use a shared or multi-user machine. The tool keeps records locally and does not show network behavior, but you should ensure the ledger directory and file are owner-only, for example with a restrictive umask or chmod 700 on the directory and chmod 600 on the ledger.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/expense-tracker.sh:16
Finding

Financial Ledger Created Without Restrictive File Permissions

Content
View full analysis
Remediation
View remediation
"$LEDGER" fi chmod 600 -- "$LEDGER" ``` 4. Validate that the data directory and ledger are owned by the current user. Refuse to continue if either has an unexpected owner. 5. Reject symbolic links for the ledger before writing to it, reducing the risk of unintended writes if the storage path is manipulated: ```bash if [ -L "$LEDGER" ]; then echo "Refusing to use a symbolic-link ledger" >&2 exit 1 fi ``` 6. Apply these protections before any ledger creation, append, read, or deletion operation so that all commands use the same secured storage path. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language description forces a specific language presentation, which can violate language/locale policy when no user opt-in or alternative is provided. The rest of the document continues in Chinese, reinforcing that the skill assumes a fixed language rather than offering a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script's description, usage text, and all user-facing messages are written in Chinese, which imposes a specific language on users without any opt-in or alternative. This matches the language/locale policy violation category because the file does not document that it is region-specific or provide a user-selectable language option.

Content

No source excerpt is available for this finding.