ai-personalization-prompts
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns, obfuscation, or unauthorized access attempts were found. The skill is purely informational.
- [NO_CODE] (SAFE): The skill consists entirely of Markdown files providing prompt templates. There are no associated scripts (.py, .js, .sh), binaries, or package manifests.
- [INDIRECT_PROMPT_INJECTION] (LOW):
- Ingestion points: The prompts ingest untrusted external data through variables like
{{companyDomain}}and{{companyDescription}}inreferences/prompts.md. - Boundary markers: No specific delimiters or instructions are used to separate user data from the system instructions.
- Capability inventory: The skill possesses no executable capabilities (no file system access, no network requests, no command execution). Consequently, an injection attack has no functional path to cause harm beyond generating malformed text.
- Sanitization: No sanitization or validation of the input variables is performed within the prompts.
Audit Metadata