Back to skill

Security audit

Algernon Sprint

Security checks for vulnerabilities and agentic risk

Overview

This skill runs a local timed study-review workflow and its data access and logging are aligned with that purpose, though users should know it records sprint metrics locally.

Install only if you want an OpenAlgernon sprint workflow that uses the specified local study database and records sprint results in a local conversation log. Review or adjust the hardcoded database path and logging behavior if this is not your environment or if you do not want study-performance metrics retained.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
94% confidence
Finding

The trigger phrases are broad enough to match normal study-related conversation, which can cause the skill to activate without clear user intent. Because this skill initiates a timed workflow and later persists session metadata, accidental invocation can lead to unexpected actions and data handling the user did not explicitly request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill appends session details to a conversation log without informing the user or obtaining consent, creating an undisclosed persistence channel for behavioral data. Even though the stored fields appear limited, they reveal study habits, timing, and performance metrics, which may be sensitive in an educational context and can violate user expectations around privacy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.