Daily Recap

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a daily recap tool, but it may read Discord content and persist broad personal work summaries without enough scoping or privacy safeguards.

Install only if you are comfortable with a recap skill reading work-session details and possibly Discord messages, then saving summaries into your Obsidian vault. Before use, set clear boundaries for which sources, channels, and dates it may read, and ask it to redact secrets, personal data, credentials, and confidential project details.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly instructs the agent to read recent Discord messages when the memory log is sparse, but the skill metadata/description does not warn users that Discord content may be accessed. This creates a consent and transparency gap: users may invoke a recap expecting local-memory summarization only, while the skill may silently collect additional conversation data from another source.

Ssd 3

Medium

Confidence: 95% confidence
Finding: The workflow directs the agent to aggregate all daily activity, including user requests, research, created artifacts, decisions, and optionally Discord messages, and then persist that summary to an Obsidian vault. This broad collection and durable storage materially increases the chance that sensitive prompts, secrets, internal discussions, or personal data are retained in natural language and later exposed through vault access, sync, or accidental sharing.

Ssd 3

Medium

Confidence: 96% confidence
Finding: The rule to 'faithfully quote the gist' of Ryan's requests increases the likelihood that sensitive user-provided information is reproduced verbatim or near-verbatim in persistent notes. Even if the original request contained secrets, confidential project details, or personal information, this instruction encourages preserving them rather than abstracting or redacting them.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal