reflexion
Cross-session learning through guided dialogue. Extracts session insights and integrates into persistent memory when session knowledge should be preserved. Alias: Reflexion.
98
Pending
Does it follow best practices?
Impact
92%
2.19xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
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
Insecure credential handling detected (high risk: 0.90). The skill instructs agents to read session JSONL files and extract/write insights into persistent memory files (and pass session contents to subagents) without any redaction or secret-handling rules, which can cause user-provided API keys/passwords or tokens in sessions to be copied verbatim into outputs.
- Repository
- jongwony/epistemic-protocols
- Commit
9342160
- 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.