Back to skill

Security audit

hindsight-bias

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a coherent hindsight-bias review workflow with proportionate recordkeeping suggestions.

Choose which records to provide and where decision notes should be kept. Review the audience and remove confidential details before sharing predictions or attributed judgments in a forum.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

The documentation workflow includes publishing predictions to an internal forum without a privacy or audience warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

Step 5 includes logging a public prediction to an internal forum alongside decision records containing who, what, when, why, and probability. The skill does not warn that posting this information can expose attributed judgments or confidential decision details to other forum members.

Content

No source excerpt is available for this finding.