Security audit

Project Weekly Report

Security checks for vulnerabilities and agentic risk

Overview

This skill reads local repository evidence to draft weekly project reports, with no code execution beyond read-only git inspection and no persistence.

Install this if you want an agent to inspect git history and selected repository files to write weekly reports. Be aware that broad requests like status summary may activate it, and ask for a different language if you do not want the default Chinese report format.

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

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation text contains broad phrases like 'weekly update', 'status summary', and requests to summarize repository progress, which can match many ordinary summarization tasks. This can cause the skill to activate in contexts the user did not intend, leading the agent to inspect local repository state, git history, and uncommitted artifacts more often than necessary and increasing the chance of unintended data exposure.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill instructs the agent to 'Write in Chinese by default' unless the user provides a different template, which overrides likely user language expectations without explicit opt-in. While not directly enabling code execution or data exfiltration, it can degrade usability, miscommunicate security-relevant output, and cause the agent to ignore the user's implicit language context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file specifies that the skill should provide a detailed Chinese report and a brief version under 300 Chinese characters, without indicating that this should depend on user preference or locale. This can cause unwanted language coercion, reduce usability, and potentially lead to misleading outputs when users expect another language, though it is not a direct code-execution or data-exfiltration risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This manifest lists invocation-relevant user needs such as "summarize recent repository work" and "write a project weekly report from local evidence," but it does not define explicit trigger boundaries, exclusion conditions, or negative examples. Those phrases are broad enough that they could overlap with ordinary summarization requests unless the runtime applies additional narrowing elsewhere.
Content: No source excerpt is available for this finding.