tldr-2

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content from the tldr-pages community project. An attacker could theoretically contribute a malicious documentation page intended to influence agent behavior when the page is retrieved.
  • Ingestion points: The output generated by executing tldr <command> is incorporated into the agent's context.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the tool output.
  • Capability inventory: The skill allows execution of the tldr binary for reading pages and updating the local cache.
  • Sanitization: No explicit sanitization or filtering is applied to the retrieved documentation content.
  • [EXTERNAL_DOWNLOADS]: The command tldr --update is used to fetch documentation updates from the official tldr-pages repository on GitHub.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:34 AM
Security Audit — agent-trust-hub — tldr-2