Back to skill

Security audit

Album Release Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly about releasing albums, but it can trigger public publishing, radio deployment, service restarts, and social posts without clear approval gates.

Review this skill before installing if an agent will have access to real music, video, social, OAuth, radio, SSH, or cron-sourced credentials. Use it only with explicit release intent, require manual approval before uploads, deployment, service restart, playlist creation, premiere, and social posting, and audit any runner so JSON config is parsed as data rather than interpolated into Python source.

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 (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:103
Finding

Command Injection Through Unsafe Inline Python Interpolation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is framed for broad, one-run end-to-end release automation without strong activation boundaries or confirmation gates. In a system where agents may invoke skills from natural-language intent, this can cause accidental execution of high-impact actions like publishing, deployment, and announcement from underspecified user requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes public publishing, radio deployment, playlist creation, and social fanout behavior, but it does not present an explicit warning that these steps create irreversible or externally visible side effects. This increases the risk of accidental public release, unwanted posts, or premature distribution if the skill is triggered in the wrong context or run with incomplete review.

Content

No source excerpt is available for this finding.