context7

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it fetches and processes external documentation content.\n
  • Ingestion points: Data is retrieved from the Context7 REST API via scripts/context7.py.\n
  • Boundary markers: The script output includes simple delimiters but lacks formal delimiters with instructions to ignore embedded prompts.\n
  • Capability inventory: The skill is configured to use Bash to execute its helper script.\n
  • Sanitization: Content returned by the documentation API is printed without filtering.\n- [DATA_EXFILTRATION]: The skill performs expected network communication with context7.com to fetch library information. This behavior is documented and necessary for the skill's function.\n- [COMMAND_EXECUTION]: The skill executes a local Python script using only standard library modules and properly encodes user-supplied input to prevent injection in the API requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 08:27 PM