Back to skill

Security audit

Session Memory Manual

Security checks for vulnerabilities and agentic risk

Overview

This skill is for manually searching past sessions, but it gives broad access to private session history and uses unsafe shell-search examples, so it should be reviewed before installation.

Install only if you are comfortable with the agent searching prior OpenClaw sessions and shared memory. Use explicit session IDs, narrow date ranges, and minimal message limits; do not allow tool-history reads or memory writes unless you have reviewed the exact content to be used. Avoid using shell-based search examples with untrusted search text.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:54
Finding

Overbroad Access to Cross-Session Messages and Tool History

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:56
Finding

User-Controlled Search Terms Can Be Interpolated into Shell Commands

Content
View full analysis
Remediation
View remediation
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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README presents the skill description entirely in Chinese and does not indicate that users may interact in another language or opt into this locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file consistently presents instructions, warnings, triggers, and outputs only in Chinese. For a generally scoped skill, this effectively forces a specific language without user opt-in or an explicit statement that the skill is limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger guidance includes broad everyday phrases such as '帮我查' and '搜一下', which can cause the skill to activate on ordinary conversational requests and expand access to cross-session history or shared memory. In this skill’s context, activation leads to searching prior sessions, reading shared memory files, and potentially writing synchronized summaries, so accidental or overly-permissive triggering increases privacy and data-exposure risk across sessions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description is written entirely in Chinese in a package manifest, which can constitute a language/locale policy issue when no opt-in, alternative locale, or region-specific justification is provided. This may reduce accessibility for users who do not read that language and implicitly enforces a locale choice.

Content

No source excerpt is available for this finding.