finalize-agent-prompt

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refine external prompt files. This creates an attack surface where malicious instructions embedded in the input files could potentially influence the agent.
  • Ingestion points: External prompt files provided by the user or environment (referenced in SKILL.md requirements).
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within the input text.
  • Capability inventory: No specific tools or command execution capabilities are granted in the frontmatter or used in the instructions.
  • Sanitization: Absent. The skill does not perform validation or filtering on the content of the prompt files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:50 AM
Security Audit — agent-trust-hub — finalize-agent-prompt