cursor-animated-sites
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform a validation step by executing a Python shell command (
python3 -c ...) to parse and verify the generated HTML file. - [INDIRECT_PROMPT_INJECTION]: The skill takes untrusted data (lifecycle sequences and folder tree structures) and interpolates it into a generated HTML/JavaScript file, which may be hosted locally or on a development server.
- Ingestion points: The lifecycle/sequence input and folder tree data fields specified in the input contract in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided to protect the generation process from malicious user input.
- Capability inventory: The skill uses file system write operations and shell-based command execution for artifact validation.
- Sanitization: There are no requirements or instructions provided to sanitize, escape, or validate the user-provided data before it is embedded in the output file.
Audit Metadata