happy-platform-skills
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation instructs the agent to use CLI tools for managing the skill library, specifically 'npx hps' and 'npx sn-skills' commands for listing, searching, and loading sub-skills.
- [EXTERNAL_DOWNLOADS]: The skill components and the library itself are downloaded from established, trusted sources including the NPM registry ('happy-platform-skills') and the author's public GitHub repository ('Happy-Technologies-LLC/happy-platform-skills').
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its data processing workflow.
- Ingestion points: The agent ingests potentially untrusted text from various ServiceNow tables, including 'incident' descriptions and 'sn_customerservice_case' details, as well as journaled user comments.
- Boundary markers: Absent. The instructions do not define delimiters for external data or include directives for the agent to ignore instructions embedded within the record fields.
- Capability inventory: The skill facilitates powerful operations including arbitrary server-side JavaScript execution via the 'SN-Execute-Background-Script' tool, alongside general record creation and modification capabilities ('SN-Create-Record', 'SN-Update-Record').
- Sanitization: No explicit sanitization or content escaping is documented for the processing of external data before it is used in automation steps.
Audit Metadata