form-and-actions-in-sveltekit

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a 'Memory Protocol' section in SKILL.md that instructs the agent to execute a shell command (cat .claude/context/memory/learnings.md). This is used to maintain state between sessions by reading a local file within the agent's context directory.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of reviewing user-provided code.
  • Ingestion points: The skill targets and reads content from all .svelte files within the project directory.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from obeying instructions that might be embedded as comments within the analyzed Svelte files.
  • Capability inventory: The skill is granted powerful tools including Read, Write, and Edit, allowing it to modify the file system based on its analysis.
  • Sanitization: No sanitization or filtering logic is present to validate the content of the ingested files before they are processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:59 AM