compact-chat-history
Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history to save it. Read this skill only when the user explicitly asks to compact/summarize — system-triggered compaction injects the instructions directly without requiring a skill read.
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./backend/super-magic/agents/skills/compact-chat-history/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This skill explicitly requires assembling a large, detailed chat summary (including exact file paths, URLs, and potentially secrets) and mandates immediately passing it to a tool call (compact_chat_history), which creates a clear and high-risk data-exfiltration vector that can leak sensitive data to an external endpoint.
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 skill explicitly allows (and thereby may require) including exact secret values in the compressed "summary" when "the user already provided it in chat and the current task cannot continue without that value", and it mandates passing the full summary as a tool parameter (risking exfiltration), so the LLM may be asked to output secrets verbatim.
- Repository
- dtyq/magic
- Commit
f9973c5
- 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.