apply-package-auditor

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown instructions for the agent to follow. No shell commands, external scripts, or obfuscated content are present.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted user-provided materials, which establishes a theoretical surface for indirect prompt injection.
  • Ingestion points: User-provided CVs, Statements of Purpose, and research statements referenced in the workflow (SKILL.md).
  • Boundary markers: The skill does not instruct the agent to use specific delimiters or protective framing when processing user documents.
  • Capability inventory: The skill does not utilize any external tools or code execution capabilities, which limits the potential impact of an injection.
  • Sanitization: There are no procedures defined for the validation or sanitization of the content within the ingested documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 03:59 PM
Security Audit — agent-trust-hub — apply-package-auditor