ai-rank

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content, such as landing pages and documentation, to perform audits and rewrites, which creates a surface for indirect prompt injection.\n
  • Ingestion points: User-provided content or file paths collected in Phase 1 ("Gather Context") of the workflow described in SKILL.md.\n
  • Boundary markers: The instructions do not specify the use of delimiters or markers to separate untrusted user content from the agent's instructions.\n
  • Capability inventory: The skill is limited to generating text-based outputs (markdown and JSON) and does not utilize tools for shell execution, file system modifications, or non-whitelisted network communication.\n
  • Sanitization: There are no instructions for the agent to sanitize or escape input content before processing.\n- [NO_CODE]: The skill consists entirely of instructional markdown and configuration metadata without any accompanying scripts or executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — ai-rank