Security audit

agent-chronicle

Security checks across malware telemetry and agentic risk

Overview

This diary skill has a coherent purpose, but it asks to read session logs, send them to an external API, and store reflective memory without enough scoping or review controls.

Review before installing. Use this only with sessions you are comfortable sending to SkillBoss, verify the missing helper scripts from a trusted source before running them, keep memory integration off or link-only for sensitive work, and avoid generating entries from logs that may contain secrets, credentials, private user data, or confidential project details.

SkillSpector

By NVIDIA

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 (5)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger list includes generic terms like "journal," "quotes," "curious," and "decisions," which can cause the skill to activate in normal conversation rather than through explicit user intent. In a skill that stores diary content and may read session logs, accidental invocation increases the risk of unintended data collection or generation of sensitive reflective content.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation states that the workflow gathers context from today's session logs and sends it to `https://api.heybossai.com/v1/pilot`, but does not present a clear, prominent privacy warning or require explicit informed consent at the point of transmission. Because session logs may contain sensitive prompts, credentials, personal data, or internal context, this can lead to unanticipated external disclosure.

Ssd 3

Medium

Confidence: 90% confidence
Finding: The skill encourages persistent storage of memorable quotes, curiosity items, decisions, and relationship notes, all of which can include sensitive user communications and behavioral metadata. Persistent aggregation increases the blast radius of any later compromise, accidental sharing, or reuse in generated outputs.

Ssd 3

Medium

Confidence: 94% confidence
Finding: The generation flow explicitly instructs the script to gather context from session logs and create first-person diary entries, which materially increases the chance of summarizing confidential session material in a durable artifact. This risk is amplified because the same flow also sends content to an external API, expanding exposure beyond local storage.

Ssd 3

Medium

Confidence: 92% confidence
Finding: Memory integration allows diary summaries or even full entries to be appended into the main daily memory log, causing sensitive reflective content to spread into broader storage used by other workflows. This propagation makes access control, deletion, and later auditing harder, and can expose private interaction details to unrelated features or exports.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.