prioritize

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected. The skill is purely instructional and functions as a text-based decision-making tool.
  • [NO_CODE]: The skill consists only of a Markdown prompt template and does not include any scripts, binaries, or tool configurations.
  • [PROMPT_INJECTION]: The skill processes external data provided by the user, representing a surface for indirect prompt injection.
  • Ingestion points: User data is ingested via the $ARGUMENTS variable in the SKILL.md prompt template.
  • Boundary markers: The injected content is enclosed within <context> XML tags to provide structural separation from system instructions.
  • Capability inventory: The skill does not request or use any tools, shell commands, file writes, or network access, which effectively neutralizes the risk of harmful outcomes from injected content.
  • Sanitization: No specific sanitization or filtering logic is present for the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:29 PM
Security Audit — agent-trust-hub — prioritize