good-morning
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions create a vulnerability surface for indirect prompt injection by designating a user-provided file (
goodmorning.md) as the "source of truth" and directing the agent to follow its instructions "exactly". - Ingestion points: Untrusted workflow instructions are ingested from a file in the user's project directory.
- Boundary markers: The skill lacks delimiters or instructions to ignore potential prompts embedded within the workflow file or the data it processes.
- Capability inventory: The skill can execute SQL queries, write HTML files to the filesystem, and open applications (browser).
- Sanitization: No sanitization is performed on data retrieved from the database before it is interpolated into the HTML report template, creating a stored XSS risk if the database contains malicious payloads.
Audit Metadata