tailrocks-axum-best-practices

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions (Step 3 in SKILL.md) direct the agent to 'Load only relevant references' from external sources like runtime-trust.md and 'official Axum and Tower docs'. While these are trusted sources, the process of ingesting and acting upon external, potentially attacker-controlled content (especially when building web adapters that handle untrusted HTTP inputs) creates a potential surface for indirect prompt injection. This is classified as LOW severity as it is a characteristic of the skill's primary function to provide guidance based on external documentation.
  • [SAFE]: The skill mentions 'tailrocks-rust-best-practices' and various 'tailrocks-*' artifacts. These are identified as vendor-owned resources for the 'tailrocks' ecosystem and do not contribute to a negative verdict.
  • [SAFE]: The guidelines explicitly warn against logging secrets or request bodies (reference/lifecycle-and-testing.md) and advise redacting sensitive headers (reference/policy-and-security.md), demonstrating a security-first approach to credential handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:11 PM
Security Audit — agent-trust-hub — tailrocks-axum-best-practices