quick-view
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data into generated HTML pages without sanitization.
- Ingestion points: Data from files (e.g., _private/drafts/outreach_drafts.md) or previous agent outputs in the context.
- Boundary markers: Absent. The skill does not define delimiters or ignore embedded instructions warnings for the data it processes.
- Capability inventory: File-write (creating files in _private/views/) and command execution (using open to launch the browser).
- Sanitization: Absent. The instructions do not provide rules for escaping HTML or removing scripts from the input data before template interpolation.
- [COMMAND_EXECUTION]: The skill uses the shell open command to automatically open the generated HTML files in the user's default browser.
Audit Metadata