Security audit

Daily Standup Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes a standup-report workflow that reads development activity, with privacy considerations users should understand before use.

Install this only if you are comfortable with an agent reading recent repository and issue-tracker activity to draft standups. Use it from intended repositories, avoid broad team mode unless you have authorization, and review the generated report before sharing it.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (4)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match common workplace requests like 'status update' or 'daily report', which can cause the skill to activate in contexts where the user did not intend repository and account activity analysis. Because this skill reads local git metadata and remote PR/issue activity, accidental invocation can expose sensitive work patterns or project details beyond the user's expectation.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill immediately describes analyzing git history, pull requests, issue trackers, and branch context without a prominent warning that it will access potentially sensitive local and remote activity data. Users may not realize that invoking a productivity skill can enumerate commits, branches, uncommitted work, and issue metadata, leading to unintentional disclosure of private development information.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: Team standup mode expands the data collection scope from a single user's activity to multiple team members' commits, PRs, issues, and dependencies, but it provides no warning about the privacy implications of aggregating others' work activity. This can normalize surveillance-style reporting and disclose individuals' work patterns, blockers, or in-progress activity to someone who may not have a need to know.

Ssd 3

Medium

Confidence: 97% confidence
Finding: The team standup feature explicitly directs the agent to collect and summarize multiple users' development activity for a team lead, including cross-team dependencies. Even if the underlying systems are accessible, centralizing and redisclosing this information increases the risk of privacy violations, managerial overreach, and leakage of sensitive project details such as blockers, branch state, and review status.

Static analysis

No suspicious patterns detected.