Security audit

adaptive-eta

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local timer helper that persistently records ETA history, with no evidence of hidden network access, deception, or destructive behavior.

Install only if you are comfortable with a local helper writing timing history to ~/.adaptive-eta/. Do not put secrets or sensitive details in timer labels, and use ADAPTIVE_ETA_HOME or delete that directory if you want to relocate or clear the history.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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

Findings (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill instructs the agent to invoke a local Python script, store state under the user's home directory, and resolve an absolute path, which implies file access and environment interaction. However, the skill does not declare any explicit tool scope or allowed tools, so an agent may execute with broader-than-necessary capabilities, violating least privilege and making accidental file or environment access harder to constrain or audit.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The document is presented only in English and Chinese, with no indication that language is selectable or that these locales are intentionally limited. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The markdown states that timer state and history are stored under ~/.adaptive-eta/, which affects user data on disk. While this is mentioned as an implementation detail, there is no clear warning about persistence, retention, or privacy implications of logging task timing history.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The skill appends history entries containing labels, outcomes, and timing information to a persistent file under the user's home directory. Although the module docstring mentions where state lives, it does not clearly warn users that their task descriptions and work-history metadata will be stored persistently.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.