Security audit
summarize-outstanding-work
Security checks for vulnerabilities and agentic risk
Overview
This skill only instructs the agent to summarize unmerged repository work using normal Git and GitHub read/status commands.
Install this only if you are comfortable with the agent inspecting repository metadata such as branch names, uncommitted file names, stash descriptions, commit summaries, PR status, and small diff stats. Run it in the intended repository, and be aware that using gh may query GitHub with your existing authentication but the skill does not instruct posting, modifying, or deleting remote data.
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
- 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