skills/kelvinz/cobb/context/Gen Agent Trust Hub

context

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • PROMPT_INJECTION (SAFE): No instructions found that attempt to override agent safety or system prompts. The skill uses natural instructional language to define its documentation workflow.
  • DATA_EXFILTRATION (SAFE): The skill only interacts with local project files (tasks/context.md). It contains explicit guardrails to prevent storing secrets, API keys, or tokens. No network operations or external data transmissions are present.
  • REMOTE_CODE_EXECUTION (SAFE): No remote code execution patterns, script downloads, or package installations were detected.
  • COMMAND_EXECUTION (SAFE): The skill does not perform any shell command execution or subprocess spawning. It is purely focused on markdown file manipulation.
  • OBFUSCATION (SAFE): No hidden, encoded, or deceptive content (Base64, zero-width characters, homoglyphs) was identified in the documentation or instructions.
  • INDIRECT_PROMPT_INJECTION (LOW): While the skill ingests information from other workflows to update the context file, its capabilities are limited to file writes within a specific directory. It lacks the network or execution capabilities necessary to exploit processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM