agent-incident-postmortem
Fail
Audited by Snyk on Aug 13, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly asks for the "full request: system prompt, context, tool calls and results, output" and requires embedding the trace in the postmortem, which forces the LLM to receive and potentially reproduce any secrets (API keys, tokens, passwords) present in those traces verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata