web-info

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill runs a PowerShell script (.claude/skills/web-info/scripts/web-info.ps1) or a Python script (scripts/web-info.py) to inspect processes and read files. This is consistent with its reported functionality.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to log file ingestion.
  • Ingestion points: Accesses error.log in the Apache logs directory via scripts/web-info.ps1 and scripts/web-info.py.
  • Boundary markers: None found. Content from the logs is concatenated directly into the output stream.
  • Capability inventory: The skill leverages tool capabilities like Bash and Read, and script-level access to the file system and process list.
  • Sanitization: No validation or sanitization is applied to the log content or the .vrd configuration data before it is rendered to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:53 PM
Security Audit — agent-trust-hub — web-info