create-tldr-page
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses a fetch tool to download documentation from user-provided URLs and retrieves example files from GitHub repositories. These are used as sources for generating TLDR pages.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its processing of untrusted external content.
- Ingestion points: Documentation URLs processed via the fetch tool and user-provided context files in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters are used to separate untrusted documentation from the skill's own instructions.
- Capability inventory: The skill has the capability to fetch remote data and display the resulting content to the user in a formatted Markdown template.
- Sanitization: There is no evidence of sanitization or validation of the fetched content to prevent adversarial instructions from influencing the agent's behavior.
Audit Metadata