ClawHub
Back to skill

Security audit

Context Resume

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local workflow helper that reconstructs developer context from git and filesystem artifacts, with no executable code, network calls, or persistence.

Install only if you are comfortable with the agent inspecting local development context such as diffs, stashes, TODOs, timestamps, and recent commands. Avoid using it in repositories or shells where command history, uncommitted changes, or stashes may contain secrets unless you first exclude or clean those sources.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill describes collecting and correlating sensitive local development artifacts—including git history, diffs, stashes, terminal commands, and timestamps—without a prominent warning or consent-oriented disclosure. This is dangerous because those artifacts can contain secrets, internal project details, abandoned experiments, or sensitive operational context, and users may invoke the skill without understanding the scope of local inspection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance is very broad, encouraging use 'every morning,' after meetings, and during routine task switches without strong scoping or consent cues. In a skill that analyzes local artifacts like git state, diffs, stashes, terminal history, and file metadata, this increases the chance of unnecessary or excessive inspection of developer data beyond what is needed for a specific resume-context task.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.