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