operationalizing-misp-threat-feeds

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples require inserting a MISP Auth Key (and show it used verbatim in PyMISP constructor, curl Authorization headers, and a CLI --key flag), which would force an LLM to include user-provided secret values directly in generated commands/code.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow ingests outsider-authored free text only as structured IOC values coming from the configured MISP instance’s feeds/attributes (via misp.search(...) and restSearch/returnFormat:suricata), i.e., not from arbitrary outsider text sources like inboxes or ticket/comments directly into the agent.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs copying rule files into system directories (e.g., /etc/suricata/rules), restarting services, and placing files under /var/ossec — all actions that modify system-wide configuration and require privileged (sudo/root) access.