hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt explicitly instructs the agent to extract and persist "specific lines, values, or IDs" into working notes and preserved data, which would require the model to copy verbatim tool output (potentially including API keys, tokens, or passwords) into its generated state and outputs.
- Repository
- aden-hive/hive
- Commit
0c38749
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.