Security audit

Diagnose Scheduled Job Trigger Vs Execution Failure

Security checks for vulnerabilities and agentic risk

Overview

This skill is a cron-diagnosis guide, but it embeds fixed incident facts and recommends manually running potentially side-effecting jobs without enough safeguards.

Review before installing or using. Treat the embedded job names, dates, errors, and recovery results only as historical examples, not current evidence. Use read-only log and run-history checks first, and require explicit user approval plus staging, dry-run, idempotency, and duplicate-delivery checks before manually triggering any scheduled job.

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:32
Finding: Case-Specific Evidence Is Presented as Current, Verified Fact
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:98
Finding: Recovery Procedure Encourages Unsafe Execution of Side-Effecting Production Jobs
Content: View full analysis
Remediation: View remediation

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is very broad and maps many loosely related symptoms to automatic activation, with few exclusion criteria. That can cause the agent to invoke this skill in inappropriate contexts, steering investigations toward log inspection, task metadata, and recovery actions even when the user’s issue is not actually about scheduled-job trigger versus execution failure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.