skills/mukul975/anthropic-cybersecurity-skills/detecting-attacks-on-historian-servers/Gen Agent Trust Hub
detecting-attacks-on-historian-servers
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs network port scanning and HTTP API queries against specified historian servers to detect unauthorized access or data integrity issues.
- [EXTERNAL_DOWNLOADS]: The skill requires the standard 'requests' Python library for network communication.
- [SAFE]: The agent disables SSL certificate validation ('verify=False') in its API requests, a common practice in OT environments that increases susceptibility to person-in-the-middle attacks.
- [CREDENTIALS_UNSAFE]: Hardcoded placeholder strings are used for API credentials in example blocks; these are correctly identified as non-sensitive placeholders.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8). 1. Ingestion points: Historian API response data processed in 'SKILL.md' and 'scripts/agent.py'. 2. Boundary markers: Absent. 3. Capability inventory: Network requests and report file writing in 'scripts/agent.py'. 4. Sanitization: No escaping or validation is performed on retrieved data before it is included in the output report.
Audit Metadata