landing-pages
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content from external URLs provided in the configuration to perform analysis and generate cache files.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its core functionality of processing untrusted data from the web.
- Ingestion points: External landing page URLs defined in the YAML configuration within SKILL.md.
- Boundary markers: Absent. The skill lacks instructions to delimit or specifically ignore instructions that might be embedded in the fetched landing page content.
- Capability inventory: The agent is instructed to fetch remote content and write structured analysis files to the local .claude/skills/landing-pages/ directory.
- Sanitization: Absent. There are no specified mechanisms for sanitizing the HTML or text content retrieved from external sources before it is processed by the model.
Audit Metadata