Security audit

Compliance Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local audit logger, but it overstates the strength of its audit trail and may store sensitive activity details in mutable plaintext files.

Install only if you treat this as a convenience activity log, not as a reliable compliance, incident-response, or tamper-proof audit system. Avoid logging secrets, tokens, personal data, or detailed financial/account information unless filesystem permissions and retention are managed separately.

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 (3)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/audit.py:107
Finding: Audit History Deletion and Truncation Can Pass Integrity Verification
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/audit.py:29
Finding: Malformed Audit Files Are Silently Discarded and Overwritten
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/audit.py:15
Finding: Audit Records Are Stored in Plaintext Without Enforced Private Permissions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill documents commands that write persistent audit logs to ~/.openclaw/audit/, which is a file-write capability, but it does not declare any tool scope such as permissions or allowed-tools. This creates a transparency and least-privilege gap: an agent or reviewer may invoke the skill without an explicit understanding that it can modify local state and persist potentially sensitive operational data.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill advertises an 'immutable' audit trail, but the implementation only maintains a locally stored hash chain over mutable JSON files. This mismatch is dangerous because operators may rely on the logs for governance or incident response, even though a local attacker can edit history and preserve internal consistency by recalculating hashes.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The code rewrites the entire audit file with normal local file permissions in a user-writable directory, so any process with the same user privileges can alter, truncate, or replace the log and then recompute the hash chain. Because there is no append-only storage, external anchoring, signature, or protected write path, the claimed tamper-evidence is weak and can be bypassed by an attacker who can modify local files.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.