ClawHub
Back to skill

Security audit

Open source problem-solving workflow

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate issue-checking purpose, but its broad automatic trigger and unsafe curl example create review-worthy risk before installation.

Install only if you are comfortable with the agent automatically checking public issue trackers for open-source debugging. Treat error messages as potentially sensitive before searching, prefer the built-in web-search tool or structured HTTP parameters over the provided curl snippet, and do not paste secrets or private stack traces into external searches.

A.I.G

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
SKILL.md:36
Finding

Shell Command Injection Through Untrusted Search Parameters

Content
View full analysis
Remediation
View remediation
&2 exit 1 ;; esac curl --silent --get \ --data-urlencode "q=repo:${org}/${repo} ${keywords} state:all" \ --data-urlencode "sort=updated" \ --data-urlencode "order=desc" \ "https://api.github.com/search/issues" | head -100 ``` Invoke the script with arguments through an execution API that preserves argument boundaries rather than assembling a shell command string. ]]>

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest says to use the skill whenever encountering bugs, errors, or unexpected behavior in any open-source project, with a long non-exhaustive list of examples. This activation scope is very broad and lacks clear exclusion criteria or negative examples, so it could collide with many ordinary debugging situations and cause unintended invocation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

Use web-search or Bash with curl to search GitHub:

bash
# Search GitHub issues via API
curl -s "https://api.github.com/search/issues?q=repo:{org}/{repo}+{keywords}+state:all&sort=updated&order=desc" | head -100

Or use web search:

Static analysis

No suspicious patterns detected.