Security audit

Cathedral Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent audit-and-fix purpose, but it asks agents to create code changes, run shell-enabled delegated sessions, and install an unspecified recurring cron monitor without enough scoping or cleanup.

Install only if you are comfortable with the agent modifying the repository, running build commands, creating commits, and potentially adding a recurring cron monitor. Before using it, prefer replacing the cron step with in-session monitoring, use secure per-run temporary files instead of /tmp/task.md, and limit delegated tools to the current tier's actual needs.

A.I.G

Vulnerability Patterns

System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
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)

T06 · System Persistence

Error

Location: SKILL.md:84
Finding: Unbounded Recurring Cron Job Creates Cross-Session Persistence
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:82
Finding: Predictable Shared Temporary File Controls a Shell-Enabled Delegated Agent
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly instructs launching a subordinate CC session with Edit,Write,Read,Bash, which enables repository modification and shell command execution. While this appears operational rather than malicious, it lacks an explicit safety warning, confirmation gate, or scoping controls, so a user could invoke the skill without clearly understanding that it may execute commands and mutate the repo.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.