skills/sickn33/agentic-awesome-skills/sankhya-dashboard-html-jsp-custom-best-pratices/Gen Agent Trust Hub
sankhya-dashboard-html-jsp-custom-best-pratices
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided JSP, HTML, and SQL files (e.g., "Analise este JSP do meu widget do Sankhya"). This creates an attack surface where instructions embedded within the user's data could influence the agent's behavior.
- Ingestion points: User-provided JSP scripts, HTML5 components, and SQL query files processed during code review or generation tasks.
- Boundary markers: The skill instructions do not explicitly require the use of delimiters (e.g., XML tags or triple backticks) to separate user data from the agent's own instructional context.
- Capability inventory: The agent can generate executable JSP code, SQL queries via the
snk:querytag, and JavaScript logic for UI interaction. - Sanitization: While the skill provides excellent patterns for sanitizing SQL parameters (removing quotes and providing fallbacks), it does not include instructions for the agent to sanitize or validate the structural integrity of the code it is analyzing to prevent secondary injection during the analysis phase.
Audit Metadata