ClawHub
Back to skill

Security audit

Insight Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill records and lists local insight notes as disclosed, with no evidence of hidden network access, credential use, privilege escalation, or destructive behavior.

Install only if you want an agent to keep local Markdown records of insights and preferences for later retrieval. Review what gets saved, avoid storing secrets or sensitive personal details unless intended, and be aware that records persist until manually removed or archived.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description presents an end-user capability for managing and analyzing insights. The supplied code chunk instead implements a test harness for the skill: it checks for SKILL.md, YAML frontmatter, required metadata fields, reference files, script executability, and runs add-insight.sh in a temporary directory to validate basic behavior and shell-safety. While this supports the overall skill implementation, the code itself does not provide the described tracking/search/analysis functionality. Because the actual code chunk’s primary purpose is materially different from the declared purpose, this is a mismatch.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · scripts/test.sh (reported line 85)May include surrounding context.

sh
if INSIGHT_DATA_DIR="$TEST_DATA_DIR" "$SKILL_DIR/scripts/add-insight.sh" '$(touch /tmp/insight-owned)' --tags test --priority low --source test >/dev/null 2>&1; then
    if [[ -f /tmp/insight-owned ]]; then
        echo "  ❌ FAIL: user content was evaluated by the shell"
        rm -f /tmp/insight-owned
        exit 1
    fi
    echo "  ✅ PASS: user content is written literally"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file presents user-facing instructions and examples in Chinese, while the rest of the document is in English, and it does not state that the skill is region- or language-specific. This can effectively impose a locale/language preference without explicit user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The "When to Use" section says to use the skill when the user asks to "track" or "record" something, which overlaps with common conversational language and may cause unintended activation. It does not provide exclusion conditions or clearer constraints to distinguish ordinary note-taking from this specific skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.