analyzing-threat-landscape-with-misp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs configuring and passing a MISP API key directly (example: --api-key YOUR_KEY) which would require the agent/LLM to accept and embed secret values verbatim in commands, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly connects to a user-specified MISP instance and fetches events via PyMISP (see scripts/agent.py fetch_events using misp.search and the SKILL.md run command with --misp-url), ingesting event attributes and tags (user-contributed/untrusted content) that are parsed and used to drive analysis and reporting, so third-party content can materially influence results and downstream actions.