Security audit
PRDigest
Security checks for vulnerabilities and agentic risk
Overview
This skill only guides the agent to turn validated PRDigest facts into prose, with clear limits on installation, secrets, and external actions.
Before installing, confirm you already trust and have configured the separate PRDigest Ruby gem, because this skill relies on that local CLI and its existing repository/service access. The skill itself is narrowly scoped and tells the agent not to install software, reveal secrets, query GitHub directly, send Telegram messages, or use AI-provider output.
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
Static analysis
No suspicious patterns detected.