context7-research

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/new_report.py) to generate markdown reports. This script performs file system operations, including creating directories and writing files to the local disk based on user-supplied input strings.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes content from external documentation sources via the Context7 MCP. This content is used to populate report templates without sanitization.\n
  • Ingestion points: mcp__context7__query-docs tool output.\n
  • Boundary markers: None present to delimit untrusted documentation content.\n
  • Capability inventory: Local file writing via scripts/new_report.py (SKILL.md).\n
  • Sanitization: No validation or escaping of the retrieved documentation content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 04:55 AM
Security Audit — agent-trust-hub — context7-research