optimizing-descriptions

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The "Workflow" section provides a bash and awk script to extract description fields from multiple SKILL.md files for bulk auditing.
  • [PROMPT_INJECTION]: The skill processes external description text, creating a surface for indirect prompt injection if those descriptions contain malicious instructions.
  • Ingestion points: SKILL.md files in subdirectories via the provided awk script.
  • Boundary markers: None; the script extracts raw text from YAML frontmatter.
  • Capability inventory: The skill performs local file reading and mentions use of the waxa CLI tool.
  • Sanitization: No sanitization is performed on the extracted description content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:01 AM
Security Audit — agent-trust-hub — optimizing-descriptions