context-mode

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions and templates for generating and running scripts in JavaScript, Python, and Shell to analyze data. Evidence in references/patterns-javascript.md and references/patterns-shell.md shows the use of fetch for API calls and execSync for executing system tools like jest and tsc.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted data from external sources.
  • Ingestion points: Data is ingested through tools like ctx_execute, ctx_execute_file, and ctx_fetch_and_index (as seen in SKILL.md).
  • Boundary markers: There are no explicit instructions for using delimiters or boundary markers to prevent the data from being interpreted as instructions by the analysis scripts.
  • Capability inventory: The skill utilizes ctx_execute which allows for arbitrary code execution and system command access via shell.
  • Sanitization: The skill does not define specific sanitization or validation steps for the external data before it is processed by generated scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 12:07 AM