Security audit

Work Receipt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper that summarizes local coding work; it has privacy considerations but no hidden execution, network use, persistence, or destructive behavior in the inspected artifact.

Install only if you are comfortable with the agent summarizing local repository activity, diffs, TODOs, tests, and relevant command context. Use it intentionally, and redact or avoid including secrets, credentials, confidential paths, or unrelated terminal history in generated receipts.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly states it analyzes git history, file changes, test results, terminal commands, and filesystem artifacts, but the description does not clearly warn users that potentially sensitive local activity and command history may be inspected. In practice, this can lead to unanticipated exposure of secrets, internal paths, credentials typed into terminals, or confidential project details in generated summaries.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The 'When to Invoke' section uses broad conditions such as 'End of every work session,' 'Before standup,' and 'Before creating a PR' without defining clear boundaries, required context, or exclusions. In a markdown skill description, this can create ambiguous activation scope and increase the chance of unintended invocation during ordinary workflow conversations.

Static analysis

No suspicious patterns detected.