NYC
skills/am-will/codex-skills/context7/Gen Agent Trust Hub

context7

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [Data Exposure & Exfiltration] (LOW): The script scripts/context7.py performs network requests to context7.com, which is not included in the list of trusted external domains; however, this is necessary for the skill's primary operation.
  • [Indirect Prompt Injection] (LOW): The skill processes documentation content from an external API which may contain instructions that influence the agent's behavior. 1. Ingestion points: Documentation text and JSON responses from context7.com (scripts/context7.py). 2. Boundary markers: Absent; raw API data is printed directly to the output. 3. Capability inventory: Network requests using the Python standard library. 4. Sanitization: None; the script returns raw results from the API without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 10:16 AM