html-plan
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from conversations and plan documents to generate an output file.
- Ingestion points: Conversation logs and project instructions as referenced in SKILL.md.
- Boundary markers: The skill does not provide instructions to use delimiters or ignore directives within the source material.
- Capability inventory: The skill creates a self-contained HTML file on the local filesystem and returns the absolute path.
- Sanitization: There are no explicit sanitization or escaping instructions for user-provided content before it is interpolated into the HTML/JavaScript structure.
- [DYNAMIC_EXECUTION]: The skill dynamically generates files containing executable code.
- Evidence: SKILL.md instructs the agent to include inline JavaScript for UI functionality such as navigation and disclosure elements.
Audit Metadata